On the sample complexity of entropic optimal transport
From MaRDI portal
Publication:6403296
arXiv2206.13472MaRDI QIDQ6403296FDOQ6403296
Philippe Rigollet, Austin J. Stromme
Publication date: 27 June 2022
Abstract: 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.
This page was built for publication: On the sample complexity of entropic optimal transport
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6403296)
