Minimax Statistical Learning with Wasserstein Distances
As opposed to standard empirical risk minimization (ERM), distributionally robust optimization aims to minimize the worst-case risk over a larger ambiguity set containing the original empirical distribution of the training data. In this work, we describe a minimax framework for statistical learning with ambiguity sets given by balls in Wasserstein space. In particular, we prove generalization bounds that involve the covering number properties of the original ERM problem. As an illustrative example, we provide generalization guarantees for transport-based domain adaptation problems where the Wasserstein distance between the source and target domain distributions can be reliably estimated from unlabeled samples.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationGeneralization BoundsSimilar Papers 제목 키워드 기반
Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances
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 th…
Numerical IntegrationMinimax-Optimal Two-Sample Test with Sliced Wasserstein
We study the problem of nonparametric two-sample testing using the sliced Wasserstein (SW) distance. While prior theoretical and empirical work indicates that the SW distance offers a promising balance between strong sta…
Computational EfficiencyTwo-sample testingControlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning
Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances between probability distributions that have …
Nonparametric Density Estimation & Convergence Rates for GANs under Besov IPM Losses
We study the problem of estimating a nonparametric probability density under a large family of losses called Besov IPMs, which include, for example, $\mathcal{L}^p$ distances, total variation distance, and generalization…
Density EstimationMinimax Distribution Estimation in Wasserstein Distance
The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis. This paper provides upper and lower …
BIG-bench Machine Learning