activity
20162026
most citedGeneralization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints

53 citations · 109 across the 27 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

stat.ML2019★ 1 cited

Sampling for Bayesian Mixture Models: MCMC with Polynomial-Time Mixing

Wenlong Mou, Nhat Ho, Martin J. Wainwright +2

We study the problem of sampling from the power posterior distribution in Bayesian Gaussian mixture models, a robust version of the classical posterior. This power posterior is kno…

stat.ML2019★ 14 cited

An Efficient Sampling Algorithm for Non-smooth Composite Potentials

Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright +1

We consider the problem of sampling from a density of the form , where is a smooth and strongly convex func…

math.ST2019

A Diffusion Process Perspective on Posterior Contraction Rates for Parameters

Wenlong Mou, Nhat Ho, Martin J. Wainwright +2

We analyze the posterior contraction rates of parameters in Bayesian models via the Langevin diffusion process, in particular by controlling moments of the stochastic process and t…

stat.ML2019

High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm

Wenlong Mou, Yi-An Ma, Martin J. Wainwright +2

We propose a Markov chain Monte Carlo (MCMC) algorithm based on third-order Langevin dynamics for sampling from distributions with log-concave and smooth densities. The higher-orde…

math.PR2019

Improved Bounds for Discretization of Langevin Diffusions: Near-Optimal Rates without Convexity

Wenlong Mou, Nicolas Flammarion, Martin J. Wainwright +1

We present an improved analysis of the Euler-Maruyama discretization of the Langevin diffusion. Our analysis does not require global contractivity, and yields polynomial dependence…