74
0

Differential Contrastive Divergence

Abstract

We formulate a differential version of contrastive divergence for continuous configuration spaces by considering a limit of MCMC processes in which the proposal distribution becomes infinitesimal. This leads to a deterministic differential contrastive divergence update -- one in which no stochastic sampling is required. We prove convergence of differential contrastive divergence in general and prove convergence to the optimal parameter value under natural but restrictive assumptions.

View on arXiv
Comments on this paper