Superquantiles at Work: Machine Learning Applications and Efficient Subgradient Computation

R. Tyrell Rockafellar and his collaborators introduced, in a series of works, new regression modeling methods based on the notion of superquantile (or conditional value-at-risk). These methods have been influential in economics, finance, management science, and operations research in general. Recent...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Set-valued and variational analysis Jg. 29; H. 4; S. 967 - 996
Hauptverfasser: Laguel, Yassine, Pillutla, Krishna, Malick, Jérôme, Harchaoui, Zaid
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Dordrecht Springer Netherlands 01.12.2021
Springer Nature B.V
Springer
Schlagworte:
Algorithms
Analysis
Convex and Variational Analysis
Machine learning
Mathematics
Mathematics and Statistics
Operations research
Optimization
Optimization and Control
Robustness (mathematics)
SI: Optimization
Robust optimization
Superquantiles
Smoothing
Machine learning
ISSN:1877-0533, 1877-0541
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:R. Tyrell Rockafellar and his collaborators introduced, in a series of works, new regression modeling methods based on the notion of superquantile (or conditional value-at-risk). These methods have been influential in economics, finance, management science, and operations research in general. Recently, they have been subject of a renewed interest in machine learning, to address issues of distributional robustness and fair allocation. In this paper, we review some of these new applications of the superquantile, with references to recent developments. These applications involve nonsmooth superquantile-based objective functions that admit explicit subgradient calculations. To make these superquantile-based functions amenable to the gradient-based algorithms popular in machine learning, we show how to smooth them by infimal convolution and detail numerical procedures to compute the gradients of the smooth approximations. We put the approach into perspective by comparing it to other smoothing techniques and by illustrating it on toy examples.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1877-0533
1877-0541
DOI:10.1007/s11228-021-00609-w