Relaxations for inference in restricted Boltzmann machines

Sida Wang, Roy Frostig, Percy Liang, Christopher D. Manning

Research output: Contribution to conferencePaper

Abstract

We propose a randomized relax-and-round inference algorithm that samples near-MAP configurations of a binary pairwise Markov random field. We experiment on MAP inference tasks in several restricted Boltzmann machines. We also use our underlying sampler to estimate the log-partition function of restricted Boltzmann machines and compare against other sampling-based methods.

Original languageEnglish (US)
StatePublished - Jan 1 2014
Externally publishedYes
Event2nd International Conference on Learning Representations, ICLR 2014 - Banff, Canada
Duration: Apr 14 2014Apr 16 2014

Conference

Conference2nd International Conference on Learning Representations, ICLR 2014
CountryCanada
CityBanff
Period4/14/144/16/14

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Linguistics and Language
  • Language and Linguistics
  • Education

Fingerprint Dive into the research topics of 'Relaxations for inference in restricted Boltzmann machines'. Together they form a unique fingerprint.

  • Cite this

    Wang, S., Frostig, R., Liang, P., & Manning, C. D. (2014). Relaxations for inference in restricted Boltzmann machines. Paper presented at 2nd International Conference on Learning Representations, ICLR 2014, Banff, Canada.