← Back to papers
2009 NIPS NeurIPS 2009

Learning in Markov Random Fields using Tempered Transitions

Abstract

Markov random fields (MRFs), or undirected graphical models, provide a powerful framework for modeling complex dependencies among random variables. Maximum likelihood learning in MRFs is hard due to the presence of the global normalizing constant. In this paper we consider a class of stochastic approximation algorithms of Robbins-Monro type that uses Markov chain Monte Carlo to do approximate maximum likelihood learning. We show that using MCMC operators based on tempered transitions enables the stochastic approximation algorithm to better explore highly multimodal distributions, which considerably improves parameter estimates in large densely-connected MRFs. Our results on MNIST and NORB datasets demonstrate that we can successfully learn good generative models of high-dimensional, richly structured data and perform well on digit and object recognition tasks.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning and Mathematics & Optimization
📈 Trend Setter — Generative Models
🧭 Keyword Pioneer — mcmc methods
🐣 Hot Topic Early Bird — generative model
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio
🌱 Topic Pioneer — Generative Models

Authors

Ruslan Salakhutdinov

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Learning Types > Unsupervised Learning Machine Learning > Optimization & Theory > Stochastic Processes Deep Learning > Models > Generative Models Mathematics & Optimization > Optimization > Stochastic Methods Machine Learning > Core Methods > Graphical Models Machine Learning > Optimization & Theory > Stochastic Methods Machine Learning > Bayesian & Probabilistic > Markov Chain Monte Carlo Deep Learning > Learning Types > Generative Models

Keywords

maximum likelihood mcmc sampling stochastic approximation mcmc methods generative model markov random field monte carlo method maximum likelihood learning tempered transition
Download PDF

Related papers

Solving Stochastic Games 2009
Bilinear classifiers for visual recognition 2009
Zero-shot Learning with Semantic Output Codes 2009
Matrix Completion from Power-Law Distributed Samples 2009
Heavy-Tailed Symmetric Stochastic Neighbor Embedding 2009