Promit Ghoshal, University of Chicago

Description

Statistics/Probability Seminar
Speaker: Promit Ghoshal, University of Chicago
Host: Parthanil Roy
Title: Bridging Theory and Practice in Stein Variational Gradient Descent: Gaussian Approximations, Finite-Particle Rates, and Beyond
Time, day and date: 4:00:00 PM – 5:00:00 PM, Tuesday, September 09
Venue: Ramanujan Hall
Abstract: Stein Variational Gradient Descent (SVGD) has emerged as a powerful interacting particle-based algorithm for nonparametric sampling, yet its theoretical properties remain challenging to unravel. This talk delves into two complementary perspectives about SVGD. First, we explore Gaussian-SVGD, a framework that projects SVGD onto the family of Gaussian distributions via a bilinear kernel. We establish rigorous convergence results for both mean-field dynamics and finite-particle systems, demonstrating linear convergence to equilibrium in strongly log-concave settings and unifying recent algorithms for Gaussian variational inference (GVI) under a single framework. Second, we analyze the finite-particle convergence rates of SVGD in Kernelized Stein Discrepancy (KSD) and Wasserstein-2 metrics. Leveraging a novel decomposition of the relative entropy time derivative, we achieve near optimal rates with polynomial dimensional dependence and extend these results to bilinear enhanced kernels.

Location
Ramanujan Hall
Date
Tue, September 9, 2025
Start Time
4:00pm-5:00pm IST
Duration
1 hour
Priority
5-Medium
Access
Public
Updated
Wed, September 3, 2025 10:25am IST