High-Order stochastic gradient thermostats for Bayesian learning of deep models

Published

Conference Paper

© Copyright 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. Learning in deep models using Bayesian methods has generated significant attention recently. This is largely because of the feasibility of modern Bayesian methods to yield scalable learning and inference, while maintaining a measure of uncertainty in the model parameters. Stochastic gradient MCMC algorithms (SG-MCMC) are a family of diffusion-based sampling methods for large-scale Bayesian learning. In SG-MCMC, multivariate stochastic gradient thermostats (mSGNHT) augment each parameter of interest, with a momentum and a thermostat variable to maintain stationary distributions as target posterior distributions. As the number of variables in a continuous-time diffusion increases, its numerical approximation error becomes a practical bottleneck, so better use of a numerical integrator is desirable. To this end, we propose use of an efficient symmetric splitting integrator in mSGNHT, instead of the traditional Euler integrator. We demonstrate that the proposed scheme is more accurate, robust, and converges faster. These properties are demonstrated to be desirable in Bayesian deep learning. Extensive experiments on two canonical models and their deep extensions demonstrate that the proposed scheme improves general Bayesian posterior sampling, particularly for deep models.

Duke Authors

Cited Authors

  • Li, C; Chen, C; Fan, K; Carin, L

Published Date

  • January 1, 2016

Published In

  • 30th Aaai Conference on Artificial Intelligence, Aaai 2016

Start / End Page

  • 1795 - 1801

International Standard Book Number 13 (ISBN-13)

  • 9781577357605

Citation Source

  • Scopus