Affordable Access

The Convergence of Contrastive Divergences

Authors
  • Yuille, Alan L
Publication Date
Jan 25, 2006
Source
eScholarship - University of California
License
Unknown
External links

Abstract

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

Report this publication

Statistics

Seen <100 times