Entropic optimal transport is maximum-likelihood deconvolution
Statistics Theory
2018-09-19 v2 Statistics Theory
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.
Keywords
Cite
@article{arxiv.1809.05572,
title = {Entropic optimal transport is maximum-likelihood deconvolution},
author = {Philippe Rigollet and Jonathan Weed},
journal= {arXiv preprint arXiv:1809.05572},
year = {2018}
}