Optimistic Dynamic Regret Bounds

Haddouche, Maxime; Guedj, Benjamin; Wintenberger, Olivier

Document type :

Pré-publication ou Document de travail

Title :

Optimistic Dynamic Regret Bounds

Author(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]

Publication date :

2023-01-18

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Collections :

Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL

Files

2301.07530
Open access
Access the document

Optimistic Dynamic Regret Bounds BibTeX CSV Excel RIS

Files

Optimistic Dynamic Regret Bounds

BibTeX

CSV

Excel

RIS