Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ghosh, Ayon, Prashanth, L. A., Jagannathan, Krishna
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2405.20933
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910465688338432
author Ghosh, Ayon
Prashanth, L. A.
Jagannathan, Krishna
author_facet Ghosh, Ayon
Prashanth, L. A.
Jagannathan, Krishna
contents We consider the problem of estimating the Optimized Certainty Equivalent (OCE) risk from independent and identically distributed (i.i.d.) samples. For the classic sample average approximation (SAA) of OCE, we derive mean-squared error as well as concentration bounds (assuming sub-Gaussianity). Further, we analyze an efficient stochastic approximation-based OCE estimator, and derive finite sample bounds for the same. To show the applicability of our bounds, we consider a risk-aware bandit problem, with OCE as the risk. For this problem, we derive bound on the probability of mis-identification. Finally, we conduct numerical experiments to validate the theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2405_20933
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Concentration Bounds for Optimized Certainty Equivalent Risk Estimation
Ghosh, Ayon
Prashanth, L. A.
Jagannathan, Krishna
Machine Learning
We consider the problem of estimating the Optimized Certainty Equivalent (OCE) risk from independent and identically distributed (i.i.d.) samples. For the classic sample average approximation (SAA) of OCE, we derive mean-squared error as well as concentration bounds (assuming sub-Gaussianity). Further, we analyze an efficient stochastic approximation-based OCE estimator, and derive finite sample bounds for the same. To show the applicability of our bounds, we consider a risk-aware bandit problem, with OCE as the risk. For this problem, we derive bound on the probability of mis-identification. Finally, we conduct numerical experiments to validate the theoretical findings.
title Concentration Bounds for Optimized Certainty Equivalent Risk Estimation
topic Machine Learning
url https://arxiv.org/abs/2405.20933