On Combining Graph-based Variance Reduction schemes

Vibhav Gogate, Rina Dechter
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:257-264, 2010.

Abstract

In this paper, we consider two variance reduction schemes that exploit the structure of the primal graph of the graphical model: Rao-Blackwellised w-cutset sampling and AND/OR sampling. We show that the two schemes are orthogonal and can be combined to further reduce the variance. Our combination yields a new family of estimators which trade time and space with variance. We demonstrate experimentally that the new estimators are superior, often yielding an order of magnitude improvement over previous schemes on several benchmarks.

Cite this Paper


BibTeX
@InProceedings{pmlr-v9-gogate10a, title = {On Combining Graph-based Variance Reduction schemes}, author = {Gogate, Vibhav and Dechter, Rina}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {257--264}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/gogate10a/gogate10a.pdf}, url = {https://proceedings.mlr.press/v9/gogate10a.html}, abstract = {In this paper, we consider two variance reduction schemes that exploit the structure of the primal graph of the graphical model: Rao-Blackwellised w-cutset sampling and AND/OR sampling. We show that the two schemes are orthogonal and can be combined to further reduce the variance. Our combination yields a new family of estimators which trade time and space with variance. We demonstrate experimentally that the new estimators are superior, often yielding an order of magnitude improvement over previous schemes on several benchmarks.} }
Endnote
%0 Conference Paper %T On Combining Graph-based Variance Reduction schemes %A Vibhav Gogate %A Rina Dechter %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-gogate10a %I PMLR %P 257--264 %U https://proceedings.mlr.press/v9/gogate10a.html %V 9 %X In this paper, we consider two variance reduction schemes that exploit the structure of the primal graph of the graphical model: Rao-Blackwellised w-cutset sampling and AND/OR sampling. We show that the two schemes are orthogonal and can be combined to further reduce the variance. Our combination yields a new family of estimators which trade time and space with variance. We demonstrate experimentally that the new estimators are superior, often yielding an order of magnitude improvement over previous schemes on several benchmarks.
RIS
TY - CPAPER TI - On Combining Graph-based Variance Reduction schemes AU - Vibhav Gogate AU - Rina Dechter BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-gogate10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 257 EP - 264 L1 - http://proceedings.mlr.press/v9/gogate10a/gogate10a.pdf UR - https://proceedings.mlr.press/v9/gogate10a.html AB - In this paper, we consider two variance reduction schemes that exploit the structure of the primal graph of the graphical model: Rao-Blackwellised w-cutset sampling and AND/OR sampling. We show that the two schemes are orthogonal and can be combined to further reduce the variance. Our combination yields a new family of estimators which trade time and space with variance. We demonstrate experimentally that the new estimators are superior, often yielding an order of magnitude improvement over previous schemes on several benchmarks. ER -
APA
Gogate, V. & Dechter, R.. (2010). On Combining Graph-based Variance Reduction schemes. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:257-264 Available from https://proceedings.mlr.press/v9/gogate10a.html.

Related Material