Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections

Abstract

Optimal transport maps between two probability distributions $\mu$ and $\nu$ on ${\mathbb{R}}^d$ have found extensive applications in both machine learning and statistics. In practice, these maps need to be estimated from data sampled according to $\mu$ and $\nu$. Plug-in estimators are perhaps most popular in estimating transport maps in the field of computational optimal transport. In this paper, we provide a comprehensive analysis of the rates of convergences for general plug-in estimators defined via barycentric projections. Our main contribution is a new stability estimate for barycentric projections which proceeds under minimal smoothness assumptions and can be used to analyze general plug-in estimators. We illustrate the usefulness of this stability estimate by first providing rates of convergence for the natural discrete-discrete and semi-discrete estimators of optimal transport maps. We then use the same stability estimate to show that, under additional smoothness assumptions of Besov type or Sobolev type, wavelet based or kernel smoothed plug-in estimators respectively speed up the rates of convergence and significantly mitigate the curse of dimensionality suffered by the natural discrete-discrete/semi-discrete estimators. As a by-product of our analysis, we also obtain faster rates of convergence for plug-in estimators of $W_2(\mu ,\nu )$, the Wasserstein distance between $\mu$ and $\nu$, under the aforementioned smoothness assumptions, thereby complementing recent results in Chizat et al. (2020). Finally, we illustrate the applicability of our results in obtaining rates of convergence for Wasserstein barycenters between two probability distributions and obtaining asymptotic detection thresholds for some recent optimal-transport based tests of independence.

arXiv comment40 pages

References in corpus (20)

• Auto-Encoding Variational Bayes
• Fast Computation of Wasserstein Barycenters
• DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
• Generative Moment Matching Networks
• Learning with a Wasserstein Loss
• Bayesian Inference with Optimal Maps
• A consistent multivariate test of association based on ranks of distances
• Optimal Transport with Proximal Splitting
• Learning in Implicit Generative Models
• Differential Properties of Sinkhorn Approximation for Learning with Wasserstein Distance
• Stochastic Wasserstein Barycenters
• Improving GANs Using Optimal Transport
• Statistical Optimal Transport via Factored Couplings
• Optimal transportation and the falsifiability of incompletely specified economic models
• Measuring Association on Topological Spaces Using Kernels and Geometric Graphs
• On the Optimality of Gaussian Kernel Based Nonparametric Tests against Smooth Alternatives
• On parameter estimation with the Wasserstein distance
• Multivariate Brenier cumulative distribution functions and their application to non-parametric testing
• Minimax optimality of permutation tests
• Convex Regression in Multidimensions: Suboptimality of Least Squares Estimators

Cited by in corpus (2)

• Entropic estimation of optimal transport maps
• Uniform Confidence Band for Optimal Transport Map on One-Dimensional Data