Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein DistancesDownload PDF

Published: 31 Oct 2022, 18:00, Last Modified: 14 Jan 2023, 18:14NeurIPS 2022 AcceptReaders: Everyone
Keywords: sliced optimal transport, Wasserstein distances, empirical convergence, robust statistics
TL;DR: The scalability of sliced optimal transport is quantified via new empirical convergence rates, robust estimation risks, and computational bounds.
Abstract: Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. The goal of this work is to quantify this scalability from three key aspects: (i) empirical convergence rates; (ii) robustness to data contamination; and (iii) efficient computational methods. For empirical convergence, we derive fast rates with explicit dependence of constants on dimension, subject to log-concavity of the population distributions. For robustness, we characterize minimax optimal, dimension-free robust estimation risks, and show an equivalence between robust sliced 1-Wasserstein estimation and robust mean estimation. This enables lifting statistical and algorithmic guarantees available for the latter to the sliced 1-Wasserstein setting. Moving on to computational aspects, we analyze the Monte Carlo estimator for the average-sliced distance, demonstrating that larger dimension can result in faster convergence of the numerical integration error. For the max-sliced distance, we focus on a subgradient-based local optimization algorithm that is frequently used in practice, albeit without formal guarantees, and establish an $O(\epsilon^{-4})$ computational complexity bound for it. Our theory is validated by numerical experiments, which altogether provide a comprehensive quantitative account of the scalability question.
Supplementary Material: pdf
18 Replies