Foundations of Probability and Statistical Machine Learning

This course provides a graduate-level introduction to advanced statistical modeling concepts and techniques that recur across contemporary computer science, with a focus on machine learning and data science. Topics include random variables, concentration inequalities, random processes, statistical inference, elements of information theory, and foundations of statistical machine learning, including empirical risk minimization, model capacity-generalization tradeoffs, and regularization, with additional topics as time allows. Prerequisites: undergraduate probability at the level of CSCI 2244 Randomness & Computation; linear algebra; multivariable calculus.