Search Results for author: Gonzalo Mena

Found 4 papers, 2 papers with code

Sinkhorn EM: An Expectation-Maximization algorithm based on entropic optimal transport

no code implementations30 Jun 2020 Gonzalo Mena, Amin Nejatbakhsh, Erdem Varol, Jonathan Niles-Weed

We study Sinkhorn EM (sEM), a variant of the expectation maximization (EM) algorithm for mixtures based on entropic optimal transport.

Sinkhorn Permutation Variational Marginal Inference

no code implementations pproximateinference AABI Symposium 2019 Gonzalo Mena, Erdem Varol, Amin Nejatbakhsh, Eviatar Yemini, Liam Paninski

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.

Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem

1 code implementation NeurIPS 2019 Gonzalo Mena, Jonathan Weed

We prove several fundamental statistical bounds for entropic OT with the squared Euclidean cost between subgaussian probability measures in arbitrary dimension.

Learning Latent Permutations with Gumbel-Sinkhorn Networks

2 code implementations ICLR 2018 Gonzalo Mena, David Belanger, Scott Linderman, Jasper Snoek

Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data.

Cannot find the paper you are looking for? You can Submit a new open access paper.