Time

9am, Tuesday, April 16, 2024

Location

Rice 414

Speaker

Chen-Yu Wei

Title:

The Multiplicative Weights Update Algorithm and its Applications

Abstract:

The multiplicative weights update (MWU) algorithm is a simple and classic algorithm that has found its applications in many areas, such as online decision making, optimization, and machine learning. In this talk, I will present its original form in the “learning from experts” problem, and then show how it can be applied to solving two-player zero-sum games, linear programming, and boosting. The talk is mostly based on the survey paper by Arora et al. (2012).

Sanjeev Arora, Elad Hazan, Satyen Kale. The multiplicative weights update method: a meta algorithm and applications. 2012.

Speaker bio:

Chen-Yu Wei is an assistant professor at the Computer Science department, University of Virginia. His research focuses on interactive decision making, reinforcement learning, and learning in games.