MATH 7740

Statistical Learning Theory

Course Description

Course information provided by the Courses of Study 2024-2025. Courses of Study 2024-2025 is scheduled to publish mid-June.

Learning theory has become an important topic in modern statistics. This course gives an overview of various topics in classification, starting with Stone's (1977) stunning result that there are classifiers that are universally consistent. Other topics include classification, plug-in methods (k-nearest neighbors), reject option, empirical risk minimization, Vapnik-Chervonenkis theory, fast rates via Mammen and Tsybakov's margin condition, convex majorizing loss functions, RKHS methods, support vector machines, lasso type estimators, low-rank multivariate response regression, random matrix theory, topic models, latent factor models, and interpolation methods in high dimensional statistics.

When Offered Fall.

Permission Note Enrollment limited to: graduate students.
Prerequisites/Corequisites Prerequisite: basic mathematical statistics (STSCI 6730/MATH 6730 or equivalent) and measure theoretic probability (MATH 6710), or permission of instructor.

View Enrollment Information