Bayes Reading Group: Neha Wadia (Flatiron CCM)

Friday Jan 31, 2025, 11:00 AM → 12:00 PM America/New_York

3rd Floor Conference Room ( 162 Fifth Avenue )

Discussion Lead: Neha Wadia (Flatiron CCM)

Topic: A mixing time bound for Gibbs sampling from log-smooth log-concave distributions

Link: https://arxiv.org/abs/2412.17899

Abstract: The Gibbs sampler, also known as the coordinate hit-and-run algorithm, is a Markov chain that is widely used to draw samples from probability distributions in arbitrary dimensions. At each iteration of the algorithm, a randomly selected coordinate is resampled from the distribution that results from conditioning on all the other coordinates. We study the behavior of the Gibbs sampler on the class of log-smooth and strongly log-concave target distributions supported on ℝn. Assuming the initial distribution is M-warm with respect to the target, we show that the Gibbs sampler requires at most … steps to produce a sample with error no more than γ