Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

arXiv2008.05367MaRDI QIDQ6346963

Guang Lin, Liyao Gao, Qi Feng, Faming Liang, Wei Deng

Publication date: 12 August 2020

Abstract: Replica exchange Monte Carlo (reMC), also known as parallel tempering, is an important technique for accelerating the convergence of the conventional Markov Chain Monte Carlo (MCMC) algorithms. However, such a method requires the evaluation of the energy function based on the full dataset and is not scalable to big data. The na"ive implementation of reMC in mini-batch settings introduces large biases, which cannot be directly extended to the stochastic gradient MCMC (SGMCMC), the standard sampling method for simulating from deep neural networks (DNNs). In this paper, we propose an adaptive replica exchange SGMCMC (reSGMCMC) to automatically correct the bias and study the corresponding properties. The analysis implies an acceleration-accuracy trade-off in the numerical discretization of a Markov jump process in a stochastic environment. Empirically, we test the algorithm through extensive experiments on various setups and obtain the state-of-the-art results on CIFAR10, CIFAR100, and SVHN in both supervised learning and semi-supervised learning tasks.

Has companion code repository: https://github.com/WayneDW/Variance_Reduced_Replica_Exchange_SGMCMC

This page was built for publication: Non-convex Learning via Replica Exchange Stochastic Gradient MCMC

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6346963)