291 search results - page 1 / 59 » The Convergence of Contrastive Divergences |
NIPS
2004
13 years 5 months ago
2004
This paper analyses the Contrastive Divergence algorithm for learning statistical parameters. We relate the algorithm to the stochastic approximation literature. This enables us t...
JMLR
2010
12 years 11 months ago
2010
Contrastive Divergence (CD) is a popular method for estimating the parameters of Markov Random Fields (MRFs) by rapidly approximating an intractable term in the gradient of the lo...
JMLR
2010
12 years 11 months ago
2010
Composite likelihood methods provide a wide spectrum of computationally efficient techniques for statistical tasks such as parameter estimation and model selection. In this paper,...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
ICML
2010
IEEE
13 years 5 months ago
2010
IEEE
Learning undirected graphical models such as Markov random fields is an important machine learning task with applications in many domains. Since it is usually intractable to learn...