Entropic optimal transport is maximum-likelihood deconvolution

Philippe Rigollet, Jonathan Weed

Research output: Contribution to journalArticlepeer-review

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.

Original languageEnglish (US)
Pages (from-to)1228-1235
Number of pages8
JournalComptes Rendus Mathematique
Volume356
Issue number11-12
DOIs
StatePublished - Nov 1 2018

ASJC Scopus subject areas

  • General Mathematics

Fingerprint

Dive into the research topics of 'Entropic optimal transport is maximum-likelihood deconvolution'. Together they form a unique fingerprint.

Cite this