PAC-Bayesian Bound for the Conditional Value at Risk - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

PAC-Bayesian Bound for the Conditional Value at Risk

Abstract

Conditional Value at Risk (CVAR) is a family of "coherent risk measures" which generalize the traditional mathematical expectation. Widely used in mathematical finance, it is garnering increasing interest in machine learning, e.g., as an alternate approach to regularization, and as a means for ensuring fairness. This paper presents a generalization bound for learning algorithms that minimize the CVAR of the empirical loss. The bound is of PAC-Bayesian type and is guaranteed to be small when the empirical CVAR is small. We achieve this by reducing the problem of estimating CVAR to that of merely estimating an expectation. This then enables us, as a by-product, to obtain concentration inequalities for CVAR even when the random variable in question is unbounded.
Fichier principal
Vignette du fichier
2006.14763.pdf (321.56 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02883728 , version 1 (29-06-2020)

Identifiers

Cite

Zakaria Mhammedi, Benjamin Guedj, Robert C. Williamson. PAC-Bayesian Bound for the Conditional Value at Risk. NeurIPS 2020, Dec 2020, Vancouver / Virtual, Canada. ⟨hal-02883728⟩
106 View
169 Download

Altmetric

Share

Gmail Facebook X LinkedIn More