English

Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo

Machine Learning 2019-11-05 v1 Numerical Analysis Numerical Analysis Computation Machine Learning

Abstract

As an important Markov Chain Monte Carlo (MCMC) method, stochastic gradient Langevin dynamics (SGLD) algorithm has achieved great success in Bayesian learning and posterior sampling. However, SGLD typically suffers from slow convergence rate due to its large variance caused by the stochastic gradient. In order to alleviate these drawbacks, we leverage the recently developed Laplacian Smoothing (LS) technique and propose a Laplacian smoothing stochastic gradient Langevin dynamics (LS-SGLD) algorithm. We prove that for sampling from both log-concave and non-log-concave densities, LS-SGLD achieves strictly smaller discretization error in 22-Wasserstein distance, although its mixing rate can be slightly slower. Experiments on both synthetic and real datasets verify our theoretical results, and demonstrate the superior performance of LS-SGLD on different machine learning tasks including posterior sampling, Bayesian logistic regression and training Bayesian convolutional neural networks. The code is available at \url{https://github.com/BaoWangMath/LS-MCMC}.

Keywords

Cite

@article{arxiv.1911.00782,
  title  = {Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo},
  author = {Bao Wang and Difan Zou and Quanquan Gu and Stanley Osher},
  journal= {arXiv preprint arXiv:1911.00782},
  year   = {2019}
}

Comments

27 pages, 5 figures

R2 v1 2026-06-23T12:03:06.081Z