ML Anthology

Manifold Stochastic Dynamics for Bayesian Learning

Mark Zlochin, Yoram Baram
NeCo 2001 pp. 2549-2572
doi:10.1162/089976601753196021 /neco/2001/zlochin2001neco-manifold/

Abstract

We propose a new Markov Chain Monte Carlo algorithm, which is a generalization of the stochastic dynamics method. The algorithm performs exploration of the state-space using its intrinsic geometric structure, which facilitates efficient sampling of complex distributions. Applied to Bayesian learning in neural networks, our algorithm was found to produce results comparable to the best state-of-the-art method while consuming considerably less time.

NeCo Semantic Scholar

Cite

Text

Zlochin and Baram. "Manifold Stochastic Dynamics for Bayesian Learning." Neural Computation, 2001. doi:10.1162/089976601753196021

Markdown

[Zlochin and Baram. "Manifold Stochastic Dynamics for Bayesian Learning." Neural Computation, 2001.](https://mlanthology.org/neco/2001/zlochin2001neco-manifold/) doi:10.1162/089976601753196021

BibTeX

@article{zlochin2001neco-manifold,
  title     = {{Manifold Stochastic Dynamics for Bayesian Learning}},
  author    = {Zlochin, Mark and Baram, Yoram},
  journal   = {Neural Computation},
  year      = {2001},
  pages     = {2549-2572},
  doi       = {10.1162/089976601753196021},
  volume    = {13},
  url       = {https://mlanthology.org/neco/2001/zlochin2001neco-manifold/}
}