Entropic optimal transport is maximum-likelihood deconvolution

DOI10.1016/j.crma.2018.10.010zbMath1407.62211arXiv1809.05572OpenAlexW2963527517WikidataQ128950994 ScholiaQ128950994MaRDI QIDQ1632830

Jonathan Weed, Philippe Rigollet

Publication date: 17 December 2018

Published in: Comptes Rendus. Mathématique. Académie des Sciences, Paris (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1809.05572

zbMATH Keywords

machine learningmaximum-likelihood estimationstatistical interpretationentropic optimal transportGaussian deconvolution

Mathematics Subject Classification ID

Measures of association (correlation, canonical correlation, etc.) (62H20) Learning and adaptive systems in artificial intelligence (68T05) Transport processes in time-dependent statistical mechanics (82C70)

Related Items (12)

Multivariate ranks and quantiles using optimal transport: consistency, rates and nonparametric testing ⋮ Minimax estimation of smooth densities in Wasserstein distance ⋮ Asymptotics for Semidiscrete Entropic Optimal Transport ⋮ Semi-discrete optimal transport: hardness, regularization and numerical solution ⋮ Estimation of Wasserstein distances in the spiked transport model ⋮ Recovering Latent Variables by Matching ⋮ Toward a mathematical theory of trajectory inference ⋮ An Improved Central Limit Theorem and Fast Convergence Rates for Entropic Transportation Costs ⋮ Fast convergence of empirical barycenters in Alexandrov spaces and the Wasserstein space ⋮ Recent theoretical advances in decentralized distributed convex optimization ⋮ Minimax estimation of smooth optimal transport maps ⋮ Cortically based optimal transport

Uses Software

• EMD
• Wasserstein GAN

Cites Work

• Unnamed Item
• A survey of the Schrödinger problem and some of its connections with optimal transport
• Sparse regression learning by aggregation and Langevin Monte-Carlo
• Mirror averaging with sparsity priors
• Kullback-Leibler aggregation and misspecified generalized linear models
• Exponential screening and optimal rates of sparse estimation
• On the estimation of quadratic functionals
• Learning by mirror averaging
• Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
• Optimal entropy-transport problems and a new Hellinger-Kantorovich distance between positive measures
• The earth mover's distance as a metric for image retrieval
• Deconvolution for the Wasserstein metric and geometric inference
• Optimal transport for applied mathematicians. Calculus of variations, PDEs, and modeling
• On minimum Kantorovich distance estimators
• Convolutional wasserstein distances
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Optimal Rates of Convergence for Deconvolving a Density
• Numerical resolution of an “unbalanced” mass transport problem
• Measurement Error in Nonlinear Models
• Sparse estimation by exponential weighting

This page was built for publication: Entropic optimal transport is maximum-likelihood deconvolution