MATH 619 Mathematical Methods for High-Dimensional and Discrete Data with Machine Learning Applications
Technological and scientific advances in our ability to collect, observe, and store data throughout science, engineering, and commerce call for a change in the basic understanding of how we are to learn and handle data. This course rigorously surveys the modern literature concerning the mathematical foundations of several statistical learning and inference problems. A particular emphasis is on non-asymptotic results. Topics covered include sparse recovery, high dimensional PCA, and nonparametric least squares. The aim is to develop algorithms that are effective both in theory and in applications.
Prerequisite
Graduate standing, familiarity with multivariate calculus, linear algebra, and a solid course in undergraduate probability and statistics. The knowledge of various standard results concerning probability and statistics is assumed. If you are not familiar with these standard results, please contact the instructor as soon as possible.