ELE539/COS512: Optimization for Machine Learning
Spring 2023, Mon. Wed. 09:30 am - 10:50 am, Friend Center 004
Instructor: Chi Jin Office hour: Mon. 4:00 pm - 5:00 pm
TA: Ahmed Khaled Office hour: Tue. 4:00 pm - 5:00 pm
Contents: Optimization theory---algorithms and complexity analyses
Grades: 5 problem sets (60%), 1 final exam (40%).
No late homework.
Schedule (weekly basis)
Convex Optimization:
Intro, black-box model
Subgradient methods, gradient methods
Nesterov's acceleration, momentum
Lower bounds [Homework 1 due]
Mirror descent
Stochastic algorithms, variance reduction [Homework 2 due]
Nonconvex Optimization
Eigenvector problems, power methods, Lanczos algorithm
Finding stationary point [Homework 3 due]
Escaping saddle point
Nonsmooth (weakly convex) optimization [Homework 4 due]
Minimax Optimization
Convex-concave: gradient descent ascent, extragradient method
Gradient descent with max-oracle [Homework 5 due]
Recommended Textbook
Convex Optimization: Algorithms and Complexity, by Sebastian Bubeck
Lecture Notes: Optimization for Machine Learning, by Elad Hazan
Convex Optimization, by Stephen Boyd and Lieven Vandenberghe
Related Courses
Elad Hazan, Optimization for Machine Learning
Yuxin Chen, Large-Scale Optimization for Data Science