Statistical bounds for entropic optimal transport: sample complexity and the central limit theorem

We prove several fundamental statistical bounds for entropic OT with the squared Euclidean cost between subgaussian probability measures in arbitrary dimension. First, through a new sample complexity result we establish the rate of convergence of entropic OT for empirical measures. Our analysis impr...

Full description

Bibliographic Details
Main Authors: Mena, G, Weed, J
Format: Conference item
Language:English
Published: MIT Press 2019