Printable PDF
Department of Mathematics,
University of California San Diego

****************************

Math 278C: Optimization and Data Science

Prof. Yian Ma

UCSD

MCMC, variational inference, and reverse diffusion Monte Carlo

Abstract:

I will introduce some recent progress towards understanding the scalability of Markov chain Monte Carlo (MCMC) methods and their comparative advantage with respect to variational inference. I will fact-check the folklore that "variational inference is fast but biased, MCMC is unbiased but slow". I will then discuss a combination of the two via reverse diffusion, which holds promise of solving some of the multi-modal problems. This talk will be motivated by the need for Bayesian computation in reinforcement learning problems as well as the differential privacy requirements that we face.

Host: Jiawang Nie

February 14, 2024

3:00 PM

APM 7321

****************************