MCMC vs. Variational Inference -- for Credible Learning and Decision-Making at Scale

Nov 23, 2021, 4:30 pm4:30 pm


  • Center for Statistics and Machine Learning
  • Electrical and Chemical Engineering
Event Description

Speaker: Yian Ma, University of California, San Diego
Title: MCMC vs. Variational Inference -- for Credible Learning and Decision-Making at Scale
Date: Tuesday, November 23, 2021
Time: 4:30 pm
Location: Zoom, please register HERE
Host: Chi Jin and Jason Lee

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 discuss an optimization perspective on the infinite dimensional probability space, where MCMC leverages stochastic sample paths while variational inference projects the probabilities onto a finite dimensional parameter space. Three ingredients will be the focus of this discussion: non-convexity, acceleration, and stochasticity. This line of work is motivated by epidemic prediction, where we need uncertainty quantification for credible predictions and informed decision making with complex models and evolving data.

Bio: Yian Ma is an assistant professor at the Halıcıoğlu Data Science Institute and an affiliated faculty member at the Computer Science and Engineering Department of University of California San Diego. Prior to UCSD, he spent a year as a visiting faculty at Google Research. Before that, he was a post-doctoral fellow at EECS, UC Berkeley. Yian completed his Ph.D. at University of Washington and obtained a bachelor's degree at Shanghai Jiao Tong University. His current research primarily revolves around scalable inference methods for credible machine learning. This involves designing Bayesian inference methods to quantify uncertainty in the predictions of complex models; understanding computational and statistical guarantees of inference algorithms; and leveraging these scalable algorithms to learn from time series data and perform sequential decision making tasks.