Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends

Christopher Tosh
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:840-849, 2016.

Abstract

Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machines (RBMs) and variants.

Cite this Paper

BibTeX
@InProceedings{pmlr-v48-tosh16, title = {Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends}, author = {Tosh, Christopher}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {840--849}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/tosh16.pdf}, url = {https://proceedings.mlr.press/v48/tosh16.html}, abstract = {Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machines (RBMs) and variants.} }
Endnote
%0 Conference Paper %T Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends %A Christopher Tosh %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-tosh16 %I PMLR %P 840--849 %U https://proceedings.mlr.press/v48/tosh16.html %V 48 %X Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machines (RBMs) and variants.
RIS
TY - CPAPER TI - Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends AU - Christopher Tosh BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-tosh16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 840 EP - 849 L1 - http://proceedings.mlr.press/v48/tosh16.pdf UR - https://proceedings.mlr.press/v48/tosh16.html AB - Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machines (RBMs) and variants. ER -
APA
Tosh, C.. (2016). Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:840-849 Available from https://proceedings.mlr.press/v48/tosh16.html.

Related Material