November 1, 2017, Aditya Gopalan, Indian Institute of Science

Wednesday, November 1, 2017, 4pm-5pm
8 St. Mary’s Street, PHO 404/428
Refreshments at 3:45pm

Aditya Gopalan
Indian Institute of Science

Online Learning with Structure

The talk will revisit a basic and widely employed model of sequential decision making under uncertainty called the Multi-Armed Bandit, where a decision maker must learn to optimize across several “arms” or actions, each with an unknown payoff a priori, by trial and error. The bandit also represents possibly the simplest form of reinforcement learning problem. Starting from the classical bandit problem, we will explore several variations of online learning problems with rich, complex structure, and highlight efficient algorithmic paradigms to solve them. We will also present recent results on non-parametric bandit problems with very large/infinite action sets.

Aditya Gopalan is an Assistant Professor and INSPIRE Faculty Fellow at the Indian Institute of Science, Electrical Communication Engineering. He received the Ph.D. degree in electrical engineering from The University of Texas at Austin, and the B.Tech. and M.Tech. degrees in electrical engineering from the Indian Institute of Technology Madras. He was an Andrew and Erna Viterbi Post-Doctoral Fellow at the Technion-Israel Institute of Technology. His research interests include machine learning and statistical inference, control, and algorithms for resource allocation in communication networks.

Faculty Host: Venkatesh Saligrama
Student Host: Tingting Xu