Explore no more: Improved high-probability regret bounds for non-stochastic bandits

Neu, Gergely

Document type :

Communication dans un congrès avec actes

Title :

Explore no more: Improved high-probability regret bounds for non-stochastic bandits

Author(s) :

Neu, Gergely [Auteur correspondant]
Sequential Learning [SEQUEL]

Conference title :

Advances on Neural Information Processing Systems 28 (NIPS 2015)

City :

Montreal

Country :

Canada

Start date of the conference :

2015-12-12

HAL domain(s) :

Informatique [cs]/Apprentissage [cs.LG]

English abstract : [en]

This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature ...
Show more >This work addresses the problem of regret minimization in non-stochastic multi-armed bandit problems, focusing on performance guarantees that hold with high probability. Such results are rather scarce in the literature since proving them requires a large deal of technical effort and significant modifications to the standard, more intuitive algorithms that come only with guarantees that hold on expectation. One of these modifications is forcing the learner to sample arms from the uniform distribution at least Ω(√ T) times over T rounds, which can adversely affect performance if many of the arms are suboptimal. While it is widely conjectured that this property is essential for proving high-probability regret bounds, we show in this paper that it is possible to achieve such strong results without this undesirable exploration component. Our result relies on a simple and intuitive loss-estimation strategy called Implicit eXploration (IX) that allows a remarkably clean analysis. To demonstrate the flexibility of our technique, we derive several improved high-probability bounds for various extensions of the standard multi-armed bandit framework. Finally, we conduct a simple experiment that illustrates the robustness of our implicit exploration technique.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.inria.fr/hal-01223501/document
Open access
Access the document

https://hal.inria.fr/hal-01223501/document
Open access
Access the document

https://hal.inria.fr/hal-01223501/document
Open access
Access the document

Explore no more: Improved high-probability ... BibTeX CSV Excel RIS

Files

Explore no more: Improved high-probability ...

BibTeX

CSV

Excel

RIS