Sinkhorn Permutation Variational Marginal Inference

Gonzalo Mena, Erdem Varol, Amin Nejatbakhsh, Eviatar Yemini, Liam Paninski
Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, PMLR 118:1-9, 2020.

Abstract

We address the problem of marginal inference for an exponential family defined over the set of permutation matrices. This problem is known to quickly become intractable as the size of the permutation increases, since its involves the computation of the permanent of a matrix, a #P-hard problem. We introduce Sinkhorn variational marginal inference as a scalable alternative, a method whose validity is ultimately justified by the so-called Sinkhorn approximation of the permanent. We demonstrate the effectiveness of our method in the problem of probabilistic identification of neurons in the worm C.elegans.

Cite this Paper

BibTeX
@InProceedings{pmlr-v118-mena20a, title = {Sinkhorn Permutation Variational Marginal Inference }, author = {Mena, Gonzalo and Varol, Erdem and Nejatbakhsh, Amin and Yemini, Eviatar and Paninski, Liam}, booktitle = {Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference}, pages = {1--9}, year = {2020}, editor = {Zhang, Cheng and Ruiz, Francisco and Bui, Thang and Dieng, Adji Bousso and Liang, Dawen}, volume = {118}, series = {Proceedings of Machine Learning Research}, month = {08 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v118/mena20a/mena20a.pdf}, url = {https://proceedings.mlr.press/v118/mena20a.html}, abstract = { We address the problem of marginal inference for an exponential family defined over the set of permutation matrices. This problem is known to quickly become intractable as the size of the permutation increases, since its involves the computation of the permanent of a matrix, a #P-hard problem. We introduce Sinkhorn variational marginal inference as a scalable alternative, a method whose validity is ultimately justified by the so-called Sinkhorn approximation of the permanent. We demonstrate the effectiveness of our method in the problem of probabilistic identification of neurons in the worm C.elegans.} }
Endnote
%0 Conference Paper %T Sinkhorn Permutation Variational Marginal Inference %A Gonzalo Mena %A Erdem Varol %A Amin Nejatbakhsh %A Eviatar Yemini %A Liam Paninski %B Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference %C Proceedings of Machine Learning Research %D 2020 %E Cheng Zhang %E Francisco Ruiz %E Thang Bui %E Adji Bousso Dieng %E Dawen Liang %F pmlr-v118-mena20a %I PMLR %P 1--9 %U https://proceedings.mlr.press/v118/mena20a.html %V 118 %X We address the problem of marginal inference for an exponential family defined over the set of permutation matrices. This problem is known to quickly become intractable as the size of the permutation increases, since its involves the computation of the permanent of a matrix, a #P-hard problem. We introduce Sinkhorn variational marginal inference as a scalable alternative, a method whose validity is ultimately justified by the so-called Sinkhorn approximation of the permanent. We demonstrate the effectiveness of our method in the problem of probabilistic identification of neurons in the worm C.elegans.
APA
Mena, G., Varol, E., Nejatbakhsh, A., Yemini, E. & Paninski, L.. (2020). Sinkhorn Permutation Variational Marginal Inference . Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference, in Proceedings of Machine Learning Research 118:1-9 Available from https://proceedings.mlr.press/v118/mena20a.html.

Related Material