Statistical Analysis of Wasserstein Distributionally Robust Estimators

08/04/2021
by   Jose Blanchet, et al.
0

We consider statistical methods which invoke a min-max distributionally robust formulation to extract good out-of-sample performance in data-driven optimization and learning problems. Acknowledging the distributional uncertainty in learning from limited samples, the min-max formulations introduce an adversarial inner player to explore unseen covariate data. The resulting Distributionally Robust Optimization (DRO) formulations, which include Wasserstein DRO formulations (our main focus), are specified using optimal transportation phenomena. Upon describing how these infinite-dimensional min-max problems can be approached via a finite-dimensional dual reformulation, the tutorial moves into its main component, namely, explaining a generic recipe for optimally selecting the size of the adversary's budget. This is achieved by studying the limit behavior of an optimal transport projection formulation arising from an inquiry on the smallest confidence region that includes the unknown population risk minimizer. Incidentally, this systematic prescription coincides with those in specific examples in high-dimensional statistics and results in error bounds that are free from the curse of dimensions. Equipped with this prescription, we present a central limit theorem for the DRO estimator and provide a recipe for constructing compatible confidence regions that are useful for uncertainty quantification. The rest of the tutorial is devoted to insights into the nature of the optimizers selected by the min-max formulations and additional applications of optimal transport projections.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/22/2020

On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification

Optimal transport (OT) distances are increasingly used as loss functions...
research
10/22/2020

Efficient robust optimal transport: formulations and algorithms

The problem of robust optimal transport (OT) aims at recovering the best...
research
07/04/2023

Fast Optimal Transport through Sliced Wasserstein Generalized Geodesics

Wasserstein distance (WD) and the associated optimal transport plan have...
research
01/22/2022

The Many Faces of Adversarial Risk

Adversarial risk quantifies the performance of classifiers on adversaria...
research
03/27/2023

Statistical Limit Theorems in Distributionally Robust Optimization

The goal of this paper is to develop methodology for the systematic anal...
research
06/04/2019

Confidence Regions in Wasserstein Distributionally Robust Estimation

Wasserstein distributionally robust optimization (DRO) estimators are ob...
research
06/22/2022

Robust Bayesian Recourse

Algorithmic recourse aims to recommend an informative feedback to overtu...

Please sign up or login with your details

Forgot password? Click here to reset