Relaxations for inference in restricted Boltzmann machines

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

Relaxations for inference in restricted Boltzmann machines

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

Research output: Contribution to conference › Paper › peer-review

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 language	English (US)
State	Published - Jan 1 2014
Externally published	Yes
Event	2nd International Conference on Learning Representations, ICLR 2014 - Banff, Canada Duration: Apr 14 2014 → Apr 16 2014

Conference

Conference	2nd International Conference on Learning Representations, ICLR 2014
Country/Territory	Canada
City	Banff
Period	4/14/14 → 4/16/14

All Science Journal Classification (ASJC) codes

Computer Science Applications
Linguistics and Language
Language and Linguistics
Education

Cite this

@conference{6490cb74caf44b3db297cca7d3a8c5b6,

title = "Relaxations for inference in restricted Boltzmann machines",

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.",

author = "Sida Wang and Roy Frostig and Percy Liang and Manning, \{Christopher D.\}",

year = "2014",

month = jan,

day = "1",

language = "English (US)",

note = "2nd International Conference on Learning Representations, ICLR 2014 ; Conference date: 14-04-2014 Through 16-04-2014",

}

TY - CONF

T1 - Relaxations for inference in restricted Boltzmann machines

AU - Wang, Sida

AU - Frostig, Roy

AU - Liang, Percy

AU - Manning, Christopher D.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85083952246

UR - https://www.scopus.com/pages/publications/85083952246#tab=citedBy

M3 - Paper

T2 - 2nd International Conference on Learning Representations, ICLR 2014

Y2 - 14 April 2014 through 16 April 2014

ER -

Relaxations for inference in restricted Boltzmann machines

Abstract

Conference

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this