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.

PDF NeurIPS OpenReview Semantic Scholar

Cite

Text

Vuckovic. "Nonlinear MCMC for Bayesian Machine Learning." Neural Information Processing Systems, 2022.

Markdown

[Vuckovic. "Nonlinear MCMC for Bayesian Machine Learning." Neural Information Processing Systems, 2022.](https://mlanthology.org/neurips/2022/vuckovic2022neurips-nonlinear/)

BibTeX

@inproceedings{vuckovic2022neurips-nonlinear,
  title     = {{Nonlinear MCMC for Bayesian Machine Learning}},
  author    = {Vuckovic, James},
  booktitle = {Neural Information Processing Systems},
  year      = {2022},
  url       = {https://mlanthology.org/neurips/2022/vuckovic2022neurips-nonlinear/}
}