Stochastic Optimization and Reinforcement Learning, Fall 2022
Course Outline
Time and location
Time: Tuesday, Friday 2:00  3:50pm
Location: Carnegie 208
Instructor
Yangyang Xu
Office: Amos Eaton 310
Office hour: in person, 3:50pm  4:50pm on Tuesday and Friday or by appointment
Email: xuy21@rpi.edu
Assignments
Reading materials
Primaldual stochastic gradient method for convex programs with many functional constraints, Xu, SIOPT, 2020.
Algorithms for stochastic optimization with function or expectation constraints, Lan and Zhou, COAP, 2020.
Escaping Saddles with Stochastic Gradients, Hadi Daneshmand, Jonas Kohler, Aurelien Lucchi, Thomas Hofmann, ICML, 2018.
Firstorder methods almost always avoid strict saddle points, Jason D. Lee, Ioannis Panageas, Georgios Piliouras, Max Simchowitz, Michael I. Jordan, Benjamin Recht. Math. Programming, 2019.
A hybrid stochastic optimization framework for composite nonconvex optimization. TranDinh, Pham, Phan, and Nguyen. Mathematical Programming, 2022.
Spiderboost and momentum: Faster variance reduction algorithms. Wang, Ji, Zhou, Liang, and Tarokh. NeurIPS, 2019.
Stochastic modelbased minimization of weakly convex functions, David and Drusvyatskiy, SIAM J. On Optimization, 2019.
iPiano: Inertial proximal algorithm for nonconvex optimization, Ochs, Chen, Brox, and Pock, SIAM J. On Imaging Sciences, 2014.
