Manifold Stochastic Dynamics for Bayesian Learning

Abstract

We propose a new Markov Chain Monte Carlo algorithm which is a gen(cid:173) eralization of the stochastic dynamics method. The algorithm performs exploration of the state space using its intrinsic geometric structure, facil(cid:173) itating efficient sampling of complex distributions. Applied to Bayesian learning in neural networks, our algorithm was found to perform at least as well as the best state-of-the-art method while consuming considerably less time.

Cite

Text

Zlochin and Baram. "Manifold Stochastic Dynamics for Bayesian Learning." Neural Information Processing Systems, 1999.

Markdown

[Zlochin and Baram. "Manifold Stochastic Dynamics for Bayesian Learning." Neural Information Processing Systems, 1999.](https://mlanthology.org/neurips/1999/zlochin1999neurips-manifold/)

BibTeX

@inproceedings{zlochin1999neurips-manifold,
  title     = {{Manifold Stochastic Dynamics for Bayesian Learning}},
  author    = {Zlochin, Mark and Baram, Yoram},
  booktitle = {Neural Information Processing Systems},
  year      = {1999},
  pages     = {694-700},
  url       = {https://mlanthology.org/neurips/1999/zlochin1999neurips-manifold/}
}