Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning

Code

• github.com/ruqizhang/csgmcmc
  OfficialIn paperpytorch★ 0
• github.com/WayneDW/Contour-Stochastic-Gradient-Langevin-Dynamics
  none★ 42
• github.com/cobypenso/functional_ensemble_distillation
  pytorch★ 6

Abstract

The posteriors over neural network weights are high dimensional and multimodal. Each mode typically characterizes a meaningfully different representation of the data. We develop Cyclical Stochastic Gradient MCMC (SG-MCMC) to automatically explore such distributions. In particular, we propose a cyclical stepsize schedule, where larger steps discover new modes, and smaller steps characterize each mode. We also prove non-asymptotic convergence of our proposed algorithm. Moreover, we provide extensive experimental results, including ImageNet, to demonstrate the scalability and effectiveness of cyclical SG-MCMC in learning complex multimodal distributions, especially for fully Bayesian inference with modern deep neural networks.

Tasks

Reproductions