On Limited-Memory Subsampling Strategies for Bandits

Baudry, Dorian; Russac, Yoan; Cappé, Olivier

Document type :

Communication dans un congrès avec actes

Title :

On Limited-Memory Subsampling Strategies for Bandits

Author(s) :

Baudry, Dorian [Auteur]
Scool [Scool]
Centre National de la Recherche Scientifique [CNRS]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Russac, Yoan [Auteur]
Value from Data [VALDA]
Centre National de la Recherche Scientifique [CNRS]
Département d'informatique - ENS-PSL [DI-ENS]
Cappé, Olivier [Auteur]
Value from Data [VALDA]
Centre National de la Recherche Scientifique [CNRS]
Département d'informatique - ENS-PSL [DI-ENS]

Conference title :

ICML 2021- International Conference on Machine Learning

City :

Vienna / Virtual

Country :

Autriche

Start date of the conference :

2021-07-18

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]

English abstract : [en]

There has been a recent surge of interest in nonparametric bandit algorithms based on subsampling. One drawback however of these approaches is the additional complexity required by random subsampling and the storage of the ...
Show more >There has been a recent surge of interest in nonparametric bandit algorithms based on subsampling. One drawback however of these approaches is the additional complexity required by random subsampling and the storage of the full history of rewards. Our first contribution is to show that a simple deterministic subsampling rule, proposed in the recent work of Baudry et al. (2020) under the name of "last-block subsampling", is asymptotically optimal in one-parameter exponential families. In addition, we prove that these guarantees also hold when limiting the algorithm memory to a polylogarithmic function of the time horizon. These findings open up new perspectives, in particular for non-stationary scenarios in which the arm distributions evolve over time. We propose a variant of the algorithm in which only the most recent observations are used for subsampling, achieving optimal regret guarantees under the assumption of a known number of abrupt changes. Extensive numerical simulations highlight the merits of this approach, particularly when the changes are not only affecting the means of the rewards.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Files

https://hal.archives-ouvertes.fr/hal-03265442/document
Open access
Access the document

http://arxiv.org/pdf/2106.10935
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-03265442/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-03265442/file/main.pdf
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-03265442/document
Open access
Access the document

document
Open access
Access the document

main.pdf
Open access
Access the document

2106.10935
Open access
Access the document

document
Open access
Access the document

main.pdf
Open access
Access the document

On Limited-Memory Subsampling Strategies ... BibTeX CSV Excel RIS

Files

On Limited-Memory Subsampling Strategies ...

BibTeX

CSV

Excel

RIS