Department of Mathematics,
University of California San Diego
****************************
Math 296, the Graduate Student Colloquium
Prof. Yuhua Zhu
Machine Learning Through the Lens of Differential Equations
Abstract:
In this talk, I will explore the rich interplay between differential equations and machine learning. I will highlight the use of collective dynamics and partial differential equations as powerful tools for improving machine learning algorithms and models. (i) In the first half of the talk, I will introduce a novel dynamical system that draws inspiration from collective intelligence observed in biology. This system offers a compelling alternative to gradientbased optimization. It enables gradientfree optimization to efficiently find global minimum in nonconvex optimization problems. (ii) In the second half of the talk, I will build the connection between HamiltonJacobiBellman equations and the multiarmed bandit (MAB) problems. MAB is a widely used paradigm for studying the explorationexploitation tradeoff in sequential decision making under uncertainty. This is the first work that establishes this connection in a general setting. I will present an efficient algorithm for solving MAB problems based on this connection and demonstrate its practical applications.

Host:
Jonathan Novak
February 22, 2023
4:00 PM
APM 7321
****************************