Why (and When and How) Contrastive Divergence Works
2014
Contrastive divergence (CD) is a promising method of
inferencein high dimensional distributions with intractable
normalizing constants, however, the theoretical foundations justifying its use are somewhat shaky. This document proposes a framework for understanding CD
inference, how/when it works, and provides multiple justifications for the CD moment conditions, including framing them as a variational
approximation.
Algorithmsfor performing
inferenceare discussed and are applied to social network data using an
exponential-family
random graphmodels (ERGM). The framework also provides guidance about how to construct MCMC kernels providing good CD
inference, which turn out to be quite different from those used typically to provide fast global mixing.
Keywords:
-
Correction
-
Source
-
Cite
-
Save
12
References
4
Citations
NaN
KQI