On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo

02/15/2018
by   Niladri S. Chatterji, et al.
0

We provide convergence guarantees in Wasserstein distance for a variety of variance-reduction methods: SAGA Langevin diffusion, SVRG Langevin diffusion and control-variate underdamped Langevin diffusion. We analyze these methods under a uniform set of assumptions on the log-posterior distribution, assuming it to be smooth, strongly convex and Hessian Lipschitz. This is achieved by a new proof technique combining ideas from finite-sum optimization and the analysis of sampling methods. Our sharp theoretical bounds allow us to identify regimes of interest where each method performs better than the others. Our theory is verified with experiments on real-world and synthetic datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/13/2018

Stochastic Variance-Reduced Hamilton Monte Carlo Methods

We propose a fast stochastic Hamilton Monte Carlo (HMC) method, for samp...
research
02/11/2020

Wasserstein Control of Mirror Langevin Monte Carlo

Discretized Langevin diffusions are efficient Monte Carlo methods for sa...
research
02/09/2021

A New Framework for Variance-Reduced Hamiltonian Monte Carlo

We propose a new framework of variance-reduced Hamiltonian Monte Carlo (...
research
06/19/2019

Stochastic Runge-Kutta Accelerates Langevin Monte Carlo and Beyond

Sampling with Markov chain Monte Carlo methods typically amounts to disc...
research
07/19/2022

A sharp uniform-in-time error estimate for Stochastic Gradient Langevin Dynamics

We establish a sharp uniform-in-time error estimate for the Stochastic G...
research
01/08/2023

Stochastic Langevin Monte Carlo for (weakly) log-concave posterior distributions

In this paper, we investigate a continuous time version of the Stochasti...
research
09/16/2021

Multilevel-Langevin pathwise average for Gibbs approximation

We propose and study a new multilevel method for the numerical approxima...

Please sign up or login with your details

Forgot password? Click here to reset