pith. sign in

arxiv: 1809.05572 · v2 · pith:YGHHFLN4new · submitted 2018-09-14 · 🧮 math.ST · stat.TH

Entropic optimal transport is maximum-likelihood deconvolution

Philippe Rigollet , Jonathan Weed This is my paper
classification 🧮 math.ST stat.TH
keywords entropicoptimaltransportdeconvolutionmaximum-likelihoodadoptioncalculatingcommunity
0
0 comments X
read the original abstract

We give a statistical interpretation of entropic optimal transport by showing that performing maximum-likelihood estimation for Gaussian deconvolution corresponds to calculating a projection with respect to the entropic optimal transport distance. This structural result gives theoretical support for the wide adoption of these tools in the machine learning community.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Hausdorff and Wasserstein metrics on graphs and other structured data

    math.OC 2019-06 unverdicted novelty 7.0

    Defines Hausdorff-style and Wasserstein-style metrics on C-sets, proving the latter are convex relaxations of the former and computable as linear programs.