On the sample complexity of entropic optimal transport

06/27/2022
by   Philippe Rigollet, et al.
0

We study the sample complexity of entropic optimal transport in high dimensions using computationally efficient plug-in estimators. We significantly advance the state of the art by establishing dimension-free, parametric rates for estimating various quantities of interest, including the entropic regression function which is a natural analog to the optimal transport map. As an application, we propose a practical model for transfer learning based on entropic optimal transport and establish parametric rates of convergence for nonparametric regression and classification.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/29/2022

A note on Cournot-Nash equilibria and Optimal Transport between unequal dimensions

This note is devoted to study a class of games with a continuum of playe...
research
07/25/2021

Estimation of Stationary Optimal Transport Plans

We study optimal transport problems in which finite-valued quantities of...
research
06/06/2023

Minimum intrinsic dimension scaling for entropic optimal transport

Motivated by the manifold hypothesis, which states that data with a high...
research
06/22/2023

Fitted Value Iteration Methods for Bicausal Optimal Transport

We develop a fitted value iteration (FVI) method to compute bicausal opt...
research
02/08/2020

Statistical Optimal Transport posed as Learning Kernel Embedding

This work takes the novel approach of posing the statistical Optimal Tra...
research
01/10/2022

Permuted and Unlinked Monotone Regression in ℝ^d: an approach based on mixture modeling and optimal transport

Suppose that we have a regression problem with response variable Y in ℝ^...
research
07/11/2023

Decorrelation using Optimal Transport

Being able to decorrelate a feature space from protected attributes is a...

Please sign up or login with your details

Forgot password? Click here to reset