Skip over navigation

Course Offerings

Course Evaluation Results

Course Details

Spring 2017-2018
ORF 570 / ELE 578   No Audit

Special Topics in Statistics and Operations Research - Statistical Optimization and Reinforcement Learning

Yuxin Chen
Mengdi Wang

This is a graduate course focused on research in statistical optimization and reinforcement learning, particularly in a large-scale setting. We discuss both theoretical and algorithmic tools to address these problems. Specific topics include: (1) randomized linear algebra (2) spectral method (3) tensor decomposition and mixture models (4) distributed estimation and optimization (5) complexity of Markov decision process (6) imitation learning (7) graph sparsification theory. Students are required to participate in paper surveying and presentation.

Sample reading list:
Nathan Halko, PerGunnar Martinsson, and Joel Tropp, SIA, Finding structure with randomness: Probabilistic algorithms
Martin Wainwright, 2017, Highdimensional statistics, A nonasymptotic viewpoint
Csaba Szepesvári, Synthesis lectures on artificial inte, Algorithms for reinforcement learning
Dimitri Bertsekas, Athena scientific, 2017, Dynamic programming and optimal control (4th edition)
Rich Sutton and Andrew Barto, 1998, Reinforcement Learning
Mahoney, Michael, arXiv preprint arXiv:1608.04481, 2016, Lecture Notes on Randomized Linear Algebra

Requirements/Grading:
Oral Presentation(s) - 50%
Term Paper(s) - 50%

Other Requirements:
Open to Graduate Students Only.

Schedule/Classroom assignment:

Class numberSectionTimeDaysRoomEnrollmentStatus
42442 L01 05:00:00 pm - 06:30:00 pm M   Engineering Quad A-Wing   A224   Enrolled:33 Limit:50