Asymptotics for Strassen's optimal transport problem

DOI10.1214/22-AIHP1258zbMATH Open1530.49044arXiv1912.02051OpenAlexW4388293442MaRDI QIDQ6187899FDOQ6187899

Authors: Lei Yu 

Publication date: 16 January 2024

Published in: Annales de l'Institut Henri Poincaré. Probabilités et Statistiques (Search for Journal in Brave)

Abstract: In this paper, we consider Strassen's version of optimal transport (OT) problem, which concerns minimizing the excess-cost probability (i.e., the probability that the cost is larger than a given value) over all couplings of two given distributions. We derive large deviation, moderate deviation, and central limit theorems for this problem. Our proof is based on Strassen's dual formulation of the OT problem, Sanov's theorem on the large deviation principle (LDP) of empirical measures, as well as the moderate deviation principle (MDP) and central limit theorems (CLT) of empirical measures. In order to apply the LDP, MDP, and CLT to Strassen's OT problem, nested formulas for Strassen's OT problem are derived. Based on these nested formulas and using a splitting technique, we construct asymptotically optimal solutions to Strassen's OT problem and its dual formulation.

Full work available at URL: https://arxiv.org/abs/1912.02051

zbMATH Keywords

central limit theoremoptimal transportlarge deviationmoderate deviation

Mathematics Subject Classification ID

Optimal transportation (49Q22) Large deviations (60F10) Central limit and other weak theorems (60F05)

Cites Work

• The earth mover's distance as a metric for image retrieval
• Title not available (Why is that?)
• Wasserstein dictionary learning: optimal transport-based unsupervised nonlinear dictionary learning
• On Choosing and Bounding Probability Metrics
• General state space Markov chains and MCMC algorithms
• On optimal matchings
• Asymptotics for transportation cost in high dimensions
• Mass transportation problems. Vol. 1: Theory. Vol. 2: Applications
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• The Speed of Mean Glivenko-Cantelli Convergence
• Large deviations techniques and applications.
• The integrability of the square exponential transportation cost
• The transportation cost from the uniform measure to the empirical measure in dimension \(\geq 3\)
• On the rate of convergence in Wasserstein distance of the empirical measure
• The Existence of Probability Measures with Given Marginals
• On the mean speed of convergence of empirical and occupation measures in Wasserstein distance
• A large deviation approach to some transportation cost inequalities
• Rényi Divergence and Kullback-Leibler Divergence
• Information theory. Coding theorems for discrete memoryless systems
• Central limit theorems for the Wasserstein distance between the empirical and the true distributions
• Matching random samples in many dimensions
• A New Approach to the Limit Theory of Recurrent Markov Chains
• Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
• Large and moderate deviations for matching problems and empirical discrepancies
• Large deviations, moderate deviations and LIL for empirical processes
• Title not available (Why is that?)
• Central limit theorems for empirical transportation cost in general dimension
• A PDE approach to a 2-dimensional matching problem
• Empirical optimal transport on countable metric spaces: distributional limits and statistical applications
• Inference for empirical Wasserstein distances on finite spaces
• Asymptotic Coupling and Its Applications in Information Theory
• Fundamental Limits of Communication With Low Probability of Detection
• Covert Communication Over Noisy Channels: A Resolvability Perspective

This page was built for publication: Asymptotics for Strassen's optimal transport problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6187899)