ML Anthology

The Convergence of Contrastive Divergences

Alan L. Yuille
NeurIPS 2004 pp. 1593-1600
/neurips/2004/yuille2004neurips-convergence/

Abstract

This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We relate the algorithm to the stochastic approxi- mation literature. This enables us to specify conditions under which the algorithm is guaranteed to converge to the optimal solution (with proba- bility 1). This includes necessary and sufficient conditions for the solu- tion to be unbiased.

PDF NeurIPS Semantic Scholar

Cite

Text

Yuille. "The Convergence of Contrastive Divergences." Neural Information Processing Systems, 2004.

Markdown

[Yuille. "The Convergence of Contrastive Divergences." Neural Information Processing Systems, 2004.](https://mlanthology.org/neurips/2004/yuille2004neurips-convergence/)

BibTeX

@inproceedings{yuille2004neurips-convergence,
  title     = {{The Convergence of Contrastive Divergences}},
  author    = {Yuille, Alan L.},
  booktitle = {Neural Information Processing Systems},
  year      = {2004},
  pages     = {1593-1600},
  url       = {https://mlanthology.org/neurips/2004/yuille2004neurips-convergence/}
}