Prerequisites: CS 229 or EE 231 or EE 244; graduate standing; or consent of instructor
Description: Explores efficient optimization algorithms for machine learning. Emphasizes fundamental principles, provable guarantees, and contemporary results. Includes fundamentals of optimization (first-order methods, stochastic algorithms, accelerated schemes, non-convex optimization, regularization, and black-box optimization). Also covers connections to statistical learning (empirical risk minimization, finite-sample guarantees, and high-dimensional problems).
Cross-listing: Cross-listed with CS 248.
Credit: May be taken Satisfactory (S) or No Credit (NC) with consent of instructor and graduate advisor.