Markov Chain Monte Carlo and Variational Inference: Bridging the Gap

Open Access
Authors
Publication date 2014
Book title Accepted papers: Advances in Variational Inference: NIPS 2014 Workshop: 13 December 2014, Convention and Exhibition Center, Montreal, Canada
Event NIPS Workshop on Advances in Variational Inference
Publisher NIPS Foundation
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract Recent advances in stochastic gradient variational inference have made it possible to perform variational Bayesian inference with posterior approximations containing auxiliary random variables. This enables us to explore a new synthesis of variational inference and Monte Carlo methods where we incorporate one or more steps of MCMC into our variational approximation. We describe the theoretical foundations that make this possible and show some promising first results.
Document type Conference contribution
Language English
Published at https://drive.google.com/file/d/0BwY-r_90KHY4d3ZTNDJpY3FYRS1rVEVVb3lUQzMzdk01Q2VV/view?pli=1
Downloads
mcmcvb (Submitted manuscript)
Permalink to this page
Back