THEORY & ALGORITHMS FOR DATA SCIENCE

COMPSCI 541

Course 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.

Prerequisties

(COMPSCI 200 , COMPSCI 220 , or STAT 340 ), (MATH 320 , MATH 340 , MATH 341 , or MATH 375 ), and (STAT 311 , STAT 333 , STAT 340 , MATH/STAT 309 , MATH/STAT 431 , MATH 331 , MATH 531 , or ISYE 210 ), or graduate/professional standing

Satisfies

This course does not satisfy any prerequisites.

Credits

Not Reported

Offered

Not Reported

Grade Point Average

Not Reported

Could not calculate change

Completion Rate

Not Reported

Could not calculate change

A Rate

Not Reported

Could not calculate change

Class Size

Not Reported

No change from Historical

No data available

Instructors (2025 Fall)

Sorted by ratings from Rate My Professors

Similar Courses

DATA SCIENCE PROGRAMMING II

COMPSCI 320

Intermediate approach to Data Science programming using Python. Experience with basic tabular analysis in Python is assumed. Learn to implement data structures (e.g., graphs) to efficiently represent datasets. Software-engineering tools such as version control and Python virtual environments will be introduced, with an emphasis on reproducibility of analysis. Tracing and A/B testing will be introduced as techniques for generating meaningful datasets. Introduces basic classification, clustering, optimization, and simulation techniques. Plotting and visual communication will be emphasized throughout the course.

LINEAR RANDOMIZED ALGORITHMS FOR DATA SCIENCE

STAT 772

Introduce new algorithms that leverage randomization to address the scale, speed, and sensitivity needs of modern data science. Develop the mathematical foundations of such randomized algorithms. Criticize these algorithms through the lens of computational resource utilization. Implement these algorithms to address linear problems in data science.

THEORETICAL FOUNDATIONS OF MACHINE LEARNING

COMPSCI/ECE/STAT 861

Advanced mathematical theory and methods of machine learning. Statistical learning theory, Vapnik-Chevronenkis Theory, model selection, high-dimensional models, nonparametric methods, probabilistic analysis, optimization, learning paradigms.

MATHEMATICAL METHODS IN DATA SCIENCE

MATH 535

A rigorous introduction to mathematical concepts important for modern data science. Topics include: matrix factorizations, optimization theory and algorithms, probabilistic models, finite Markov chains. Mathematical techniques are motivated by and illustrated on a range of applied problems from machine learning and statistics.

DATA EXPLORATION, CLEANING, AND INTEGRATION FOR DATA SCIENCE

COMPSCI 774

Big Data is often said to deal with four Vs: volume, velocity, variety, and veracity. The focus is on variety and veracity challenges, which often arise in data science projects. In many such projects, data is often incorrect, hard to understand, and come from a variety of sources. Data scientists often spend 80% of their effort to explore, clean, and integrate this data, before analysis can be carried out to extract insights. As a result, managing variety and veracity has received significant attention. Study these topics, understand their challenges, and discuss solutions. These solutions often require data management, machine learning, big data scaling, cloud, crowdsourcing, and user interaction techniques. Knowledge of machine learning/AI [COMP SCI 540], databases [COMP SCI 564] and Python [COMP SCI 320] recommended.