Convergence Rates for Regularized Optimal Transport via Quantization

by   Stephan Eckstein, et al.
ETH Zurich
Columbia University

We study the convergence of divergence-regularized optimal transport as the regularization parameter vanishes. Sharp rates for general divergences including relative entropy or L^p regularization, general transport costs and multi-marginal problems are obtained. A novel methodology using quantization and martingale couplings is suitable for non-compact marginals and achieves, in particular, the sharp leading-order term of entropically regularized 2-Wasserstein distance for all marginals with finite (2+δ)-moment.


page 1

page 2

page 3

page 4


Convergence rate of Tsallis entropic regularized optimal transport

In this paper, we consider Tsallis entropic regularized optimal transpor...

Entropy-regularized optimal transport on multivariate normal and q-normal distributions

Distance and divergence of the probability measures play a central role ...

On the convergence of the regularized entropy-based moment method for kinetic equations

The entropy-based moment method is a well-known discretization for the v...

Soft Quantization using Entropic Regularization

The quantization problem aims to find the best possible approximation of...

Doubly Regularized Entropic Wasserstein Barycenters

We study a general formulation of regularized Wasserstein barycenters th...

Convergence of Empirical Optimal Transport in Unbounded Settings

In compact settings, the convergence rate of the empirical optimal trans...

The Directional Optimal Transport

We introduce a constrained optimal transport problem where origins x can...

Please sign up or login with your details

Forgot password? Click here to reset