Relaxations for Inference in Restricted Boltzmann Machines

Abstract

We propose a relaxation-based approximate 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.

Cite

Text

Wang et al. "Relaxations for Inference in Restricted Boltzmann Machines." International Conference on Learning Representations, 2014.

Markdown

[Wang et al. "Relaxations for Inference in Restricted Boltzmann Machines." International Conference on Learning Representations, 2014.](https://mlanthology.org/iclr/2014/wang2014iclr-relaxations/)

BibTeX

@inproceedings{wang2014iclr-relaxations,
  title     = {{Relaxations for Inference in Restricted Boltzmann Machines}},
  author    = {Wang, Sida I. and Frostig, Roy and Liang, Percy and Manning, Christopher D.},
  booktitle = {International Conference on Learning Representations},
  year      = {2014},
  url       = {https://mlanthology.org/iclr/2014/wang2014iclr-relaxations/}
}