Distributionally robust optimization

doi:10.1017/S0962492924000084

Distributionally robust optimization

2025-07-01

8

OA

AI

DOI：10.1017/S0962492924000084

原文链接

查看原文

摘要

En 中文

Distributionally robust optimization (DRO) studies decision problems under uncertainty 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 distribution 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 research 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.

Keyword:

PROBABILISTIC COMBINATORIAL OPTIMIZATION

SEMIDEFINITE PROGRAMMING APPROACH

CONVEX RISK MEASURES

WORST-CASE VALUE

VALUE-AT-RISK

STOCHASTIC OPTIMIZATION

EMPIRICAL LIKELIHOOD

OPTIMAL TRANSPORT

LINEAR-PROGRAMS

WASSERSTEIN DISTANCE

Distributionally robust optimization

摘要

AI总结

期刊

机构

引用论文