AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC

Abstract

Stochastic gradient Hamiltonian Monte Carlo (SGHMC) is an efficient method for sampling from continuous distributions. It is a faster alternative to HMC: instead of using the whole dataset at each iteration, SGHMC uses only a subsample. This improves performance, but introduces bias that can cause SGHMC to converge to the wrong distribution. One can prevent this using a step size that decays to zero, but such a step size schedule can drastically slow down convergence. To address this tension, we propose a novel second-order SG-MCMC algorithm---AMAGOLD---that infrequently uses Metropolis-Hastings (M-H) corrections to remove bias. The infrequency of corrections amortizes their cost. We prove AMAGOLD converges to the target distribution with a fixed, rather than a diminishing, step size, and that its convergence rate is at most a constant factor slower than a full-batch baseline. We empirically demonstrate AMAGOLD's effectiveness on synthetic distributions, Bayesian logistic regression, and Bayesian neural networks.

Published at AISTATS 2020

References in corpus (7)

• Weight Uncertainty in Neural Networks
• On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators
• Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Firefly Monte Carlo: Exact MCMC with Subsets of Data
• Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration
• Semi-Implicit Variational Inference