This course will provide a self-contained introduction to the theory of machine learning and some of its currently-researched areas. The focus will be on supervised learning, where the goal is to learn good predictors from data while making few or no probabilistic assumptions. It will be roughly divided into three parts: (1) Statistical learning theory; (2) Optimization algorithms for machine learning; and (3) Theory of deep learning.
Important disclaimer: The course is theoretical in nature, aimed at students with a strong math/theoretical CS background, and focuses on theorems and proofs rather than machine learning applications.
Upon successful completion of this course students should be able to: