Distributionally Robust Losses for Latent Covariate Mixtures

John Duchi (), Tatsunori Hashimoto () and Hongseok Namkoong ()
Additional contact information
John Duchi: Departments of Electrical Engineering and Statistics, Stanford University, Stanford, California 94305
Tatsunori Hashimoto: Department of Computer Science, Stanford University, Stanford, California 94305
Hongseok Namkoong: Decision, Risk, and Operations Division, Columbia Business School, New York, New York 10027

Operations Research, 2023, vol. 71, issue 2, 649-664

Abstract: While modern large-scale data sets often consist of heterogeneous subpopulations—for example, multiple demographic groups or multiple text corpora—the standard practice of minimizing average loss fails to guarantee uniformly low losses across all subpopulations. We propose a convex procedure that controls the worst case performance over all subpopulations of a given size. Our procedure comes with finite-sample (nonparametric) convergence guarantees on the worst-off subpopulation. Empirically, we observe on lexical similarity, wine quality, and recidivism prediction tasks that our worst case procedure learns models that do well against unseen subpopulations.

Keywords: Machine Learning and Data Science; statistical learning; distributionally robust optimization; stochastic optimization (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/opre.2022.2363 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:oropre:v:71:y:2023:i:2:p:649-664

Access Statistics for this article

More articles in Operations Research from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().