[{"run_id":"20260906T231458-5fdd2fff","semester":"1272","observed_at":"2026-09-06 23:14:58.172943+00:00","record_version_id":"a6a4919e5ae0c4bdee0bcf728ab09d5c2a4bb6dc8b80b845a6bf84efe807a6d2","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"20260907T155543-ce3781c4","semester":"1272","observed_at":"2026-09-07 15:55:43.033547+00:00","record_version_id":"a6a4919e5ae0c4bdee0bcf728ab09d5c2a4bb6dc8b80b845a6bf84efe807a6d2","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-03b0bbb9723907cf3d1b41cf0bb34837dc398e42","semester":"1262","observed_at":"2025-04-16 05:20:33.104844+00:00","record_version_id":"a9bf25a4d4a028b209a517a9a927a3d5bce6afd27e5b96cc425e18d17701a213","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-0837245627eb714ae6bb0375f7abe8f41042011f","semester":"1262","observed_at":"2025-04-16 05:20:33.104844+00:00","record_version_id":"a9bf25a4d4a028b209a517a9a927a3d5bce6afd27e5b96cc425e18d17701a213","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-08c92e359bbbc110b0778b7e0b15d6f40000e6b1","semester":"1262","observed_at":"2025-08-21 07:05:14.730696+00:00","record_version_id":"68db51b9a7561add21fcfd164f9e070631bdad5c568dbaa18c7ae873c314b54b","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-0944d76440dc778fbb89626058c10451009ce9c6","semester":"1262","observed_at":"2025-05-21 03:36:18.194118+00:00","record_version_id":"305aac45c0fad5d986569110323da6159d25a944d99a4fc57d4f1a97c48ffed1","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-0a7f4bce29c816ef4d3d71b4eb8a2a3e15e33cc1","semester":"1262","observed_at":"2025-06-18 20:04:02.695444+00:00","record_version_id":"fec499cf177bc32bcbe582a74d95caf375b020c3c20cddbde04dd9014befda83","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-0ab917f827a7de22ebdc1087114d377a31c4687b","semester":"1262","observed_at":"2025-05-22 02:11:02.531191+00:00","record_version_id":"bc40010d0d117d145d2ef68986c1af4b6b083ed9f36e04d11fc56da2e26c8f98","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-0c40ecab4b6db9333d1f18aef816e3ee659e300c","semester":"1262","observed_at":"2025-05-25 18:02:34.797617+00:00","record_version_id":"bef85b66144644ac4da763ad250c804789b4db6e810e25a336abd2e128d25847","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-0cb4d29a588ec7f11c7e00b7cf5dc3a0d23d0349","semester":"1266","observed_at":"2026-01-22 01:00:26.555427+00:00","record_version_id":"9e974bf57fe4a4850345b9d7074e9ae6efb8c62b6a3e259d6e1aab2c5394937c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-11c30ec39e91498cbfcf3a923c53a4b03e387280","semester":"1262","observed_at":"2025-07-20 04:58:26.847117+00:00","record_version_id":"431a09ddbd04c95856476102f6e85ac30d2a997955753470e933c9040733b977","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-13cd500edf2587e9a3428f326253738fbea965ea","semester":"1264","observed_at":"2025-12-14 04:50:04.653658+00:00","record_version_id":"6c69d504e293e527b0efe1e57373452964358c0dd7368e4ac3d7ac4669cedb33","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-1da08b2de39f05e6bc877c189fc2fd6eeda563f5","semester":"1262","observed_at":"2025-07-01 00:03:56.707251+00:00","record_version_id":"982ec02ec8801542e2d1c02a43bb2f52564a22ac37aa45b9468df04bc8039a88","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-2031af47efe133b0e7877f433286ff07385afc41","semester":"1262","observed_at":"2025-07-02 20:16:45.749584+00:00","record_version_id":"4e45a7308a9e36be6e07a0c736e33fd2024aeb04d0ebd31ec855651a446980d9","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-238eba6f32fbc30407f616dd0628ff02a2a824dd","semester":"1262","observed_at":"2025-08-17 05:15:07.788352+00:00","record_version_id":"d80a5f6118897924553a1f3dfc49ea0ea821e7c784552e1288d06fcf0c782573","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-25f0ff56bc4d80f8a8afa1a0bcce8dae6fddb5e5","semester":"1262","observed_at":"2025-05-25 17:20:25.942090+00:00","record_version_id":"4dfda96488844ac24257b8d2976e0cabb29bf684c0f6d2e8dc09d232bc3ed915","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-2923f91826ce253b7aeefa9f75b4a39fe4c80ff0","semester":"1262","observed_at":"2025-08-10 05:10:25.938416+00:00","record_version_id":"4b25c73867655fe66f66b93c9e3300cf096f5d42a5dcf4ae10dbae0a8d20a4f4","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-2a05214a4023e0157fa6f7d188c85308f714176c","semester":"1262","observed_at":"2025-09-07 04:56:38.255315+00:00","record_version_id":"7bb65e575475c7daddfcfdaf77f5da2d098cb8229fa7b478ebb1dda017cf9c59","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-2b1b8e39131de92b94620b25c5bbb25690efed4c","semester":"1262","observed_at":"2025-06-01 07:54:53.913454+00:00","record_version_id":"8c6f116ee9dd758032f33e0b147ad075da19b7687f615060a211b245fd8091ef","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-33a1225644e5a5855d60f66e65413946e72fedf4","semester":"1262","observed_at":"2025-06-22 01:52:05.152650+00:00","record_version_id":"e1bb66617d960ecd4cdfad9fe896964924b2b737d134e8a2e796afbaa47e0bdc","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-3b89c83dbf5208e13756184de1f2b2d0c09af35f","semester":"1262","observed_at":"2025-06-30 06:40:10.235522+00:00","record_version_id":"f13573e03f9d9f59d51f109f7a6725d4eaac04227e42a31dbd6f6c0575c81730","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-3c3eebf7f35c39364b445a2fa5a112ce28dbb4a1","semester":"1262","observed_at":"2025-06-01 17:03:59.062985+00:00","record_version_id":"2e7c759c0ceb0cb815c86071bdf48c4b3a5e1d8c18bc58aedc7de7a9ceca88ae","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-3fa4dd71391f1c9cf4ab2216680bbc428689f92d","semester":"1262","observed_at":"2025-05-25 01:15:58.180530+00:00","record_version_id":"28638c09f9511577e51040bf305be1236e665008cbb4339ca9b3627042b92522","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-4040aa216da722a34483f68fc1e129ea571ae08d","semester":"1262","observed_at":"2025-06-01 07:27:39.695506+00:00","record_version_id":"a1941f9bd3419dde82b12eddb9d0dbb14cec481086908d2deeab678b3202dbc5","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-454d53cd690294459f8ad0793cc3ed562060e56c","semester":"1262","observed_at":"2025-05-25 01:34:00.536004+00:00","record_version_id":"fd788ab8f52977a4901987d80fb1727594705c469092d9a6713a38bf3a82889b","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-486f091e051fdb4ccdb80ee7b4fb0a5814510324","semester":"1264","observed_at":"2025-11-16 05:32:31.273726+00:00","record_version_id":"89c8bcedcd539ab760141f9f2b926a18f87f0f166576a46e78a6fe767dbb1983","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-50393cfc5fd5598d4f4731ef1919f2ff53af07d9","semester":"1262","observed_at":"2025-06-30 06:05:57.438846+00:00","record_version_id":"534cde51f7fc7334558274ecbd63407d89fa8e4b2939087915d24264f9767146","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-50f6947786b208c800db8bbd0cec84a8f0f187d2","semester":"1262","observed_at":"2025-06-02 03:49:42.915428+00:00","record_version_id":"f23cac135de70242b87297e893c092b3f7be405eb4b0c20b949405ab4099c65f","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-51d86ed4082dced3803c295419b0ec8440942016","semester":"1264","observed_at":"2025-11-12 04:50:41.141307+00:00","record_version_id":"90ec9d387654b81df393a2f6718719d77a2a40c3592c40e0050ae6cb7dfd8ffe","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-53101bd1c10db0d00d094e4c9154d4c244ff23d9","semester":"1262","observed_at":"2025-10-05 04:58:05.366968+00:00","record_version_id":"7ae41910e6c443f7dfbb25b73eb02d20f5313eaa7fd5eecd74ad9a829f94d5ac","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-58751151c564e11c5cb8aedd3a2d3527c22f73eb","semester":"1262","observed_at":"2025-06-01 06:59:01.536576+00:00","record_version_id":"48e5d869cd3cf310abf9a5c1bace0464cbcd8a88e5ea8832f4135bc73c6a56cd","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-5c4c8d3701a333ba4ddadef7d0b5dde8440fcdf0","semester":"1262","observed_at":"2025-06-01 01:57:51.256704+00:00","record_version_id":"358926d3533d22ff6e6020795c6f0044effaa8572d23a2700e3d8af44f7aff4f","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-5d20d9f81651d3c83fcaa2fd10870ce6e5d5a685","semester":"1262","observed_at":"2025-05-21 16:48:48.484741+00:00","record_version_id":"698f1c4a14e73c42f8ec4ec3de94561fa5243caef8fe9ff035d1d7740f2f8842","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-5feaebf2ab37051c86ad360cc0fa0d7e0e2ea295","semester":"1262","observed_at":"2025-05-24 15:58:23.378859+00:00","record_version_id":"215f3227f8e5bf649f50b8420cabfcc823d0fab0979cf56472ff57d26cc31263","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-60949965544fce098cc006354e201149005fb77b","semester":"1264","observed_at":"2025-10-26 05:07:14.077864+00:00","record_version_id":"666cf0098812286d84a5f0b04dd373385f5c8a84b2f1c12ea91994f22a3568fe","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-639225ac3addf8522f1d30cb4fe26054ea7f8c49","semester":"1262","observed_at":"2025-06-01 08:14:42.497608+00:00","record_version_id":"2ad3883f647fcaef37d9c0e3be55240668940b8cf114de2a12f8f22eb995aef6","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-64093b17b3a9c67a41aa33eb37adb53ec38df714","semester":"1262","observed_at":"2025-05-22 02:11:02.531191+00:00","record_version_id":"f6477444ba0890424c111c0633d4d727b504ea9ab227942a3c8f887738c7a23a","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-6885b56099f55e08aa0205546369fb0381d50e13","semester":"1262","observed_at":"2025-07-13 04:59:22.367394+00:00","record_version_id":"4e8c0b063d1c25ece7c39a876ebe31f691bf4089bce99bbdf6d0f8797463d7bb","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-69d4b2b16e8268f75b6390b3a0e2ce8bf73999da","semester":"1262","observed_at":"2025-06-30 03:21:29.925498+00:00","record_version_id":"febf7676cd1857b71c992de85ef2dc7f8f974c659d6e2364be2878bd3e8a3a5f","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-6b29c3e0673b2f9a736d2363db5409e03d5b3ed4","semester":"1264","observed_at":"2025-12-03 12:33:41.418072+00:00","record_version_id":"574f33e51ca944b1e3b196d8cade906f8c49336bd101d90e554242fb7b09c0d4","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-73259984748de484976ef2ad56ad7ab3d4cb4518","semester":"1262","observed_at":"2025-06-26 08:27:56.461216+00:00","record_version_id":"eb2f435c4f60b7d42ec9a9c9af6dbd49c843f5947e5ece8cbac5579b51dd6c4f","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-741602fbc6252c232a0b9e6bc1a9ae3101625f5a","semester":"1262","observed_at":"2025-06-30 22:49:32.522034+00:00","record_version_id":"0b36169dd1bf6f950bc65110d31637cc086b4168787cd5479c16844cc6b3ff88","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-7774f45558276ec29bf626e58fffb4a27bdbb2a9","semester":"1264","observed_at":"2025-11-01 11:49:36.359151+00:00","record_version_id":"4fea7cc35fb7679b8e2667de38723ddb747311feb8f4928832b354eec3d8899c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-7ab7c5e783fc8ebef8b8ee8cea019ee37a72ce74","semester":"1262","observed_at":"2025-09-28 04:58:07.340658+00:00","record_version_id":"4c1f24733bfe073caf157e114e9f53669835945010acc9292f158968c8542eef","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-7b2f22d83ea05055ab90dcb77dc802382cccc6f7","semester":"1262","observed_at":"2025-05-21 17:56:46.096741+00:00","record_version_id":"045394dbeb730fef98287711938f0fa4bc133a2a545354224a9db2be06cb457e","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-7ca1175502be18eb51f7b016818a884a43fd4ebb","semester":"1262","observed_at":"2025-07-29 06:28:23.644795+00:00","record_version_id":"946280c2cabf42bb4243fdd1044e9ee9315ddeb75e20b92689e6a94cc31d3b36","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-7d8cee5e42602ad9ba5dc0322085af2fa0dffaac","semester":"1262","observed_at":"2025-05-22 01:15:19.291664+00:00","record_version_id":"f4c328b65b182e5c488d6710f4e7718b8004b302acab65f0fe0125ec39fa5d8c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-81a0d6a7f668c98c59bd05fa988aa079c5ad1f68","semester":"1262","observed_at":"2025-05-31 07:49:50.419452+00:00","record_version_id":"a98a11e083e8ca99a8681311a18aabaa45065879812093dbffc513fc1d309b90","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-82f31c08c746a214872494cde6ecaeb9330441b4","semester":"1262","observed_at":"2025-06-17 21:26:08.547156+00:00","record_version_id":"a5d6311efbaa357e9b697813ba409dae91878b552c4566c91993dffab427e5d7","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-84c248343c5a99ab42c5616c594812a5e3e31cbb","semester":"1262","observed_at":"2025-07-04 06:00:07.487827+00:00","record_version_id":"d28fb92733c5839dc2c8dad520d9205cecce3b92a32ad22e4e3e4a25a61b155f","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-86334e7275e315853287e8580c35456c68df800b","semester":"1262","observed_at":"2025-05-22 06:53:03.336354+00:00","record_version_id":"02d93fbd395c6813dd0a9f11f9a15557cc0057888dac538f23b90bea607da699","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-8686dc1664f93a6c05f50321410961b39b12f91b","semester":"1262","observed_at":"2025-05-28 10:17:41.595894+00:00","record_version_id":"de655508a44f34656efb7f98a5e4f8584cf96f810cb2fc18a1547a35df12ae56","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-86d941366886c9a14a2581c04e20d0bdd25e1b02","semester":"1262","observed_at":"2025-08-31 04:54:14.656039+00:00","record_version_id":"47867b70043dd67a7fd81bde26d105256068e32635ff854c2dee5066e2f8f27b","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-8ba1d2e6cfbb1525b4f9f769ec164fb6ad0f237a","semester":"1262","observed_at":"2025-06-02 05:22:45.010398+00:00","record_version_id":"3864994be9c1685258699c3d8e9322055c40de44b0f008ecbb38817c76a7d132","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-90e5aa456689a3b222016c05c319bbcd0bddd453","semester":"1262","observed_at":"2025-05-25 02:00:10.037905+00:00","record_version_id":"68fd72eed45fced3586a6d4d315372d7fec1965ecac8945d289fb5314ae61d33","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-92d960aa7e4cd6e4c9ac8b2e232092904038e9e4","semester":"1262","observed_at":"2025-06-08 01:50:46.451351+00:00","record_version_id":"233c75e10aaae3c449ba28552a9747061d671ef1262d34b19e8d1dbf2c45474c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-94002ae588a8f71eca6d64105f2e603e8587293b","semester":"1262","observed_at":"2025-05-21 09:01:16.021508+00:00","record_version_id":"cb6fcab138c993df4e1322e92b681b121eb034b17563b5fee10489a020d9a062","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-9dd575e013c5c6e000ab3ad2d1288cc1dd9c96dc","semester":"1264","observed_at":"2025-12-21 04:47:46.589081+00:00","record_version_id":"89d455b63a869bcb7495cbcdcc19b164ec3c17d744ea8d51f5a1e4315645d381","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-a1ea26ed78cbd6e94bc3221e50a6ed9b6bf43871","semester":"1262","observed_at":"2025-05-25 09:16:55.180581+00:00","record_version_id":"1990e76e212c4fff8138b457959a460d22e2546702eb8ae8fdff976a345e9c38","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-a76a3505853d5ea9c13bb98472b87361d469e2ee","semester":"1262","observed_at":"2025-05-28 18:03:41.793846+00:00","record_version_id":"4ced9703f3718b6401b7cad419cd45d4d353dedbf511b2871c0a50ac38e97613","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-b285d591f6acf3aa1910e02edc297664db86eb8c","semester":"1262","observed_at":"2025-06-10 22:48:22.460295+00:00","record_version_id":"6dd8f0339bea5ced4a7b0976540ede330c50a09b115ab508aaf47e08e8043eaa","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-b79af756e4f00ba98231feb859ed8e98239eb811","semester":"1262","observed_at":"2025-05-22 02:47:56.931581+00:00","record_version_id":"7079491a12f2bf1228c3898548263c0533ddb6ae4151d25da585c56043c00915","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-b89e05b94730c6471439082d9279c0a834a4aeec","semester":"1262","observed_at":"2025-08-26 20:25:42.325239+00:00","record_version_id":"e451ea71660a9d7d4b5dc0131280b5aa9a9f1f05ddbc68b57c26d12c62a6e5f8","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-b9279a12d1f2688df9e556183c94d41a89e431dc","semester":"1262","observed_at":"2025-07-06 01:49:47.203835+00:00","record_version_id":"6b36b7520b77c6d52cde88b35fcb26f915a14c605eceabac5ae56a4697c4f18c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-bbdc905e96cc681a5e9a8b02c795b682206e36d1","semester":"1262","observed_at":"2025-06-25 08:02:45.445730+00:00","record_version_id":"c9a8de8b87deb5179ffe3d2a1426e0fd5ae7c2cc68e2be195789b5ae3ecfd2ed","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-bde225b5243a13d81827aa173e39c78a652b54a0","semester":"1262","observed_at":"2025-05-23 07:22:33.219345+00:00","record_version_id":"de81520c6a0615bb0a4951aebb4e1ab5d39a3c216d06bce5a9a100445bbdd697","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-c1fac4cbfde737f4f4ac02cdf15e6f5a9b5b676d","semester":"1262","observed_at":"2025-05-22 01:15:19.291664+00:00","record_version_id":"f4c328b65b182e5c488d6710f4e7718b8004b302acab65f0fe0125ec39fa5d8c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-c6b62be45f8a13cba109ef2a7741b9cd9a6b8272","semester":"1262","observed_at":"2025-08-24 08:48:09.035112+00:00","record_version_id":"ec78b4f4ac4c6a182d94cb53cf4065cd14fdf056e8a58871ebbc4e5825aa2bb0","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-cc83f62cb6db61f39320916d819ad48ce55cd96d","semester":"1262","observed_at":"2025-05-22 00:45:35.735230+00:00","record_version_id":"3cd6428ecaf4f139cdf4057509eb671100bec789346b7b7f243598711c29bc2a","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-d33818a01b6b4c5e2902e704da6e5b713742d4dc","semester":"1262","observed_at":"2025-10-13 10:46:24.251475+00:00","record_version_id":"34f7bb9b9538c69f25fdd5640c0a55f135c190a870ddec564e1253784f1edde2","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-d3c17db9832d3064916046caf891dd23f10b1bb9","semester":"1262","observed_at":"2025-08-26 11:30:42.288639+00:00","record_version_id":"83db970559b905221846985ddd4a23476002c09a1e47be38ab2def6504864882","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-d4ee226dc44268e9b6767fb9f5f20343322f494b","semester":"1262","observed_at":"2025-06-15 01:52:23.911697+00:00","record_version_id":"4d2bef955d2227869c8df200cde4eab43669551b8a287578fcc097288057c410","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-d8f9fc7f136e2033556d9d65bbdbdf33425dbdc9","semester":"1262","observed_at":"2025-05-28 16:48:12.400438+00:00","record_version_id":"9b5c8df55be712f58338560da49e77eb99a40fef047e747bd70a37011d0f800c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-dbbc9739c616c3846b2e796e00a36fa41225f7d8","semester":"1262","observed_at":"2025-06-01 17:47:19.325144+00:00","record_version_id":"920bac74d66f692cd117c6a4dbab361c33624bc009c6a6fdff240e83934cf526","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-dbe5f2d24b48c3177297a3d69c553cc9d1194bac","semester":"1262","observed_at":"2025-09-14 05:00:27.366070+00:00","record_version_id":"dbacbdebcecd5b96b6a5a8dacd5db5d3fad76fa04d561346fc1fa74f19c3287c","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-dd357dc2758e9e282c30988a527ce37de92593b9","semester":"1264","observed_at":"2025-10-19 01:39:41.951404+00:00","record_version_id":"91629c7fa33222e398b84b589669c6ed9d8eee6e174402d30d2ed9d8408407e0","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-de74de559e409a3fe668685e28043b888d2e6841","semester":"1262","observed_at":"2025-06-27 07:38:50.882897+00:00","record_version_id":"5980435dae0614f7f825860958a6788aad29154762e53ef7e337c64744e038c9","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-deca7188cf536ade3203cd88b52a45e92a059617","semester":"1262","observed_at":"2025-06-27 00:37:46.087071+00:00","record_version_id":"2146fbc548e3aac31211a66858c37b4cf13d5ec03f8a042c8e6f8caaefbb64b2","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-df60fa9ac3931c5612b0fa641b7a6f5fbec86fab","semester":"1262","observed_at":"2025-05-24 06:36:37.554678+00:00","record_version_id":"f1d49e0b8354fd8aef7ca8be4bedf09892cb86b725608c56f7df1429a7e40573","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-e339da2d849aaf8bb4dceca07a84728af23cf755","semester":"1262","observed_at":"2025-07-23 08:49:22.748925+00:00","record_version_id":"ff04cd41483666994d44d713afe3e9c916d9e3e9c41efd3e1adcde3a480e76ab","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-e934b1784835f5d36ae9b7ef0992b11e72c39142","semester":"1262","observed_at":"2025-06-01 06:21:25.219533+00:00","record_version_id":"408a6481dbbba14c81e5fb6c27257260f4d3a4b527d6a4ddccb2549a9c45e2b2","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-ef471690c082448deebd2687eab84b0b78813c36","semester":"1262","observed_at":"2025-06-29 01:47:56.317645+00:00","record_version_id":"d412414de3035dd334c087541fda8c0d8b28463bb6be3d99bb15c06910a30baf","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-efc4e8e2cd7c3f68e059a308990c00c77c7611eb","semester":"1264","observed_at":"2025-10-16 05:48:13.935141+00:00","record_version_id":"0a5831fc390fc2204fb41c57127a3d1c493ddafb14d674f1d39f3fdb8089438f","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"c9203df888778c797c3d6b1f9013949896d86cd700ae588ad391fe0c3b865e3d","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, placement intoCOMP SCI 300, orSTAT 340), (MATH 320,340,341,345, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"},{"run_id":"legacy-f18b7749725097d41f69c60779ff38cf073b93b3","semester":"1262","observed_at":"2025-05-21 19:52:03.259353+00:00","record_version_id":"7f09b2fcd66bd10343a66262cb07abb37d980db6f92abe191c0350d2ff056b47","course_id":"COMPSCI 541","course_uid":"course_89d31ece17cccde1ae010191","catalog_version_id":"1e49157db34c24ae313da9570714a5a174934992122da86948b29ec2f7da62c7","course_number":541,"subjects":["COMPSCI"],"title":"THEORY & ALGORITHMS FOR DATA SCIENCE","description":"Theoretical methods for data science. Topics include: review of probability background, concentration inequalities, geometry of high dimensional random variables, parametric and non-parametric estimation, selected topics from optimization (optimality conditions; deterministic and stochastic gradient descent), PAC learning, sample complexity and algorithms for linear classification and regression, and property/distribution testing. Uses Python programming language.","requirements_text":"(COMP SCI 200,220, orSTAT 340), (MATH 320,340,341, or375), and (STAT 311,333,340,MATH/​STAT  309,431,MATH 331,531, orI SY E 210), or graduate/professional standing"}]