conftrace_

2022 NeurIPS NeurIPS 2022

Nonlinear MCMC for Bayesian Machine Learning

Abstract

We explore the application of a nonlinear MCMC technique first introduced in [1] to problems in Bayesian machine learning. We provide a convergence guarantee in total variation that uses novel results for long-time convergence and large-particle (``propagation of chaos'') convergence. We apply this nonlinear MCMC technique to sampling problems including a Bayesian neural network on CIFAR10.

Authors

James Vuckovic

Topics

Machine Learning > Optimization & Theory > Bayesian Inference Machine Learning > Optimization & Theory > Stochastic Processes Machine Learning > Bayesian & Probabilistic > Markov Chain Monte Carlo

Keywords

variational inference bayesian inference convergence analysis markov chain monte carlo stochastic process bayesian neural network bayesian machine learning

More from NeurIPS 2022

All NeurIPS 2022 papers →

TransBoost: Improving the Best ImageNet Performance using Deep Transduction

Sparse Probabilistic Circuits via Pruning and Growing

Adam Can Converge Without Any Modification On Update Rules

Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions

IKEA-Manual: Seeing Shape Assembly Step by Step

M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design