Skip to main content
Download PDF
- Main
The Convergence of Contrastive Divergences
- Author(s): Yuille, Alan L
- et al.
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.