MATH-412: Statistical machine learning

Lectures in this course (49)

Explores the success and challenges of deep learning, including overfitting, generalization, and the impact on various domains.

Discusses statistical learning theory, Rademacher complexity, and empirical process control for estimation error.

Presents a proof for Rademacher control of the expected estimation error, focusing on empirical process control.

Explores Talagrand's lemma, Rademacher complexity bounds, and high probability guarantees in learning.

Explores the McDiarmid inequality and its implications in probability theory, focusing on writing variations and key concepts.

Covers the proof of bounds on empirical process deviations, focusing on mathematical derivations and inequalities.

Discusses the application of the main theorem to least square regression in a RKHS, focusing on LR of the Rademacher bound and Lipschitz constant.

Summarizes the result for linear regression and introduces Vapnik-Chervonenkis dimension and growth function.

Covers learning bounds, complexities, growth function, shattering, and VC dimension in binary classifiers.

Page 3 of 3