Optimistic Dynamic Regret Bounds

Haddouche, Maxime; Guedj, Benjamin; Wintenberger, Olivier

Type de document :

Pré-publication ou Document de travail

Titre :

Optimistic Dynamic Regret Bounds

Auteur(s) :

Haddouche, Maxime [Auteur]
Guedj, Benjamin [Auteur]

MOdel for Data Analysis and Learning [MODAL]
The Inria London Programme [Inria-London]
The Alan Turing Institute
Inria Lille - Nord Europe
Institut National de Recherche en Informatique et en Automatique [Inria]
Department of Computer science [University College of London] [UCL-CS]
University College of London [London] [UCL]
Wintenberger, Olivier [Auteur]

Date de publication :

2023-01-18

Discipline(s) HAL :

Informatique [cs]/Apprentissage [cs.LG]

Résumé en anglais : [en]

Online Learning (OL) algorithms have originally been developed to guarantee good performances when comparing their output to the best fixed strategy. The question of performance with respect to dynamic strategies remains ...
Lire la suite >Online Learning (OL) algorithms have originally been developed to guarantee good performances when comparing their output to the best fixed strategy. The question of performance with respect to dynamic strategies remains an active research topic. We develop in this work dynamic adaptations of classical OL algorithms based on the use of experts' advice and the notion of optimism. We also propose a constructivist method to generate those advices and eventually provide both theoretical and experimental guarantees for our procedures.Lire moins >

Langue :

Anglais

Collections :

Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL

Fichiers

2301.07530
Accès libre
Accéder au document

Optimistic Dynamic Regret Bounds BibTeX CSV Excel RIS

Fichiers

Optimistic Dynamic Regret Bounds

BibTeX

CSV

Excel

RIS