Distributionally robust optimization
File(s)
Accepted version
Author(s)
Kuhn, Daniel
Shafiee, Soroosh
Wiesemann, Wolfram
Type
Journal Article
Abstract
Distributionally robust optimization (DRO) studies decision problems under uncer tainty where the probability distribution governing the uncertain problem parameters
is itself uncertain. A key component of any DRO model is its ambiguity set, that
is, a family of probability distributions consistent with any available structural or
statistical information. DRO seeks decisions that perform best under the worst dis tribution in the ambiguity set. This worst case criterion is supported by findings
in psychology and neuroscience, which indicate that many decision-makers have a
low tolerance for distributional ambiguity. DRO is rooted in statistics, operations re search and control theory, and recent research has uncovered its deep connections to
regularization techniques and adversarial training in machine learning. This survey
presents the key findings of the field in a unified and self-contained manner.
is itself uncertain. A key component of any DRO model is its ambiguity set, that
is, a family of probability distributions consistent with any available structural or
statistical information. DRO seeks decisions that perform best under the worst dis tribution in the ambiguity set. This worst case criterion is supported by findings
in psychology and neuroscience, which indicate that many decision-makers have a
low tolerance for distributional ambiguity. DRO is rooted in statistics, operations re search and control theory, and recent research has uncovered its deep connections to
regularization techniques and adversarial training in machine learning. This survey
presents the key findings of the field in a unified and self-contained manner.
Date Acceptance
2024-11-06
Citation
Acta Numerica
ISSN
0962-4929
Publisher
Cambridge University Press
Journal / Book Title
Acta Numerica
Copyright Statement
Subject to copyright. This paper is embargoed until publication. Once published the author’s accepted manuscript will be made available under a CC-BY License in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy).
License URL
Publication Status
Accepted
Rights Embargo Date
10000-01-01