STOCHASTIC APPROXIMATION ALGORITHMS FOR SUPERQUANTILES ESTIMATION
hal.structure.identifier | Institut de Mathématiques de Bordeaux [IMB] | |
dc.contributor.author | BERCU, Bernard | |
hal.structure.identifier | Institut de Mathématiques de Toulouse UMR5219 [IMT] | |
dc.contributor.author | COSTA, Manon | |
hal.structure.identifier | Institut de Mathématiques de Toulouse UMR5219 [IMT] | |
dc.contributor.author | GADAT, Sébastien | |
dc.date.accessioned | 2024-04-04T02:50:25Z | |
dc.date.available | 2024-04-04T02:50:25Z | |
dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/191909 | |
dc.description.abstractEn | This paper is devoted to two different two-timescale stochastic approximation algorithms for superquantile estimation. We shall investigate the asymptotic behavior of a Robbins-Monro estimator and its convexified version. Our main contribution is to establish the almost sure convergence, the quadratic strong law and the law of iterated logarithm for our estimates via a martingale approach. A joint asymptotic normality is also provided. Our theoretical analysis is illustrated by numerical experiments on real datasets. | |
dc.language.iso | en | |
dc.title.en | STOCHASTIC APPROXIMATION ALGORITHMS FOR SUPERQUANTILES ESTIMATION | |
dc.type | Document de travail - Pré-publication | |
dc.subject.hal | Mathématiques [math] | |
dc.subject.hal | Mathématiques [math]/Probabilités [math.PR] | |
dc.subject.hal | Mathématiques [math]/Statistiques [math.ST] | |
bordeaux.hal.laboratories | Institut de Mathématiques de Bordeaux (IMB) - UMR 5251 | * |
bordeaux.institution | Université de Bordeaux | |
bordeaux.institution | Bordeaux INP | |
bordeaux.institution | CNRS | |
hal.identifier | hal-02908351 | |
hal.version | 1 | |
hal.origin.link | https://hal.archives-ouvertes.fr//hal-02908351v1 | |
bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=BERCU,%20Bernard&COSTA,%20Manon&GADAT,%20S%C3%A9bastien&rft.genre=preprint |
Fichier(s) constituant ce document
Fichiers | Taille | Format | Vue |
---|---|---|---|
Il n'y a pas de fichiers associés à ce document. |