Distributionally Robust Learning

08/20/2021
by   Ruidi Chen, et al.
0

This monograph develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust Optimization (DRO) under the Wasserstein metric. Beginning with fundamental properties of the Wasserstein metric and the DRO formulation, we explore duality to arrive at tractable formulations and develop finite-sample, as well as asymptotic, performance guarantees. We consider a series of learning problems, including (i) distributionally robust linear regression; (ii) distributionally robust regression with group structure in the predictors; (iii) distributionally robust multi-output regression and multiclass classification, (iv) optimal decision making that combines distributionally robust regression with nearest-neighbor estimation; (v) distributionally robust semi-supervised learning, and (vi) distributionally robust reinforcement learning. A tractable DRO relaxation for each problem is being derived, establishing a connection between robustness and regularization, and obtaining bounds on the prediction and estimation errors of the solution. Beyond theory, we include numerical experiments and case studies using synthetic and real data. The real data experiments are all associated with various health informatics problems, an application area which provided the initial impetus for this work.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/05/2020

Distributional Robustness and Regularization in Reinforcement Learning

Distributionally Robust Optimization (DRO) has enabled to prove the equi...
research
09/08/2019

Distributionally Robust Optimization with Correlated Data from Vector Autoregressive Processes

We present a distributionally robust formulation of a stochastic optimiz...
research
06/10/2020

Robust Grouped Variable Selection Using Distributionally Robust Optimization

We propose a Distributionally Robust Optimization (DRO) formulation with...
research
02/12/2020

The empirical duality gap of constrained statistical learning

This paper is concerned with the study of constrained statistical learni...
research
06/07/2017

Outlier Detection Using Distributionally Robust Optimization under the Wasserstein Metric

We present a Distributionally Robust Optimization (DRO) approach to outl...
research
07/19/2022

Holistic Robust Data-Driven Decisions

The design of data-driven formulations for machine learning and decision...
research
09/09/2020

Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionality

Wasserstein distributionally robust optimization (DRO) aims to find robu...

Please sign up or login with your details

Forgot password? Click here to reset