Finite-Time Analysis of Kernelised Contextual Bandits

Michal Valko 1 Nathan Korda 1 Rémi Munos 1 Ilias Flaounas 2 Nello Cristianini 2
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : We tackle the problem of online reward maximisation over a large finite set of actions described by their contexts. We focus on the case when the number of actions is too big to sample all of them even once. However we assume that we have access to the similarities between actions' contexts and that the expected reward is an arbitrary linear function of the contexts' images in the related reproducing kernel Hilbert space (RKHS). We propose KernelUCB, a kernelised UCB algorithm, and give a cumulative regret bound through a frequentist analysis. For contextual bandits, the related algorithm GP-UCB turns out to be a special case of our algorithm, and our finite-time analysis improves the regret bound of GP-UCB for the agnostic case, both in the terms of the kernel-dependent quantity and the RKHS norm of the reward function. Moreover, for the linear kernel, our regret bound matches the lower bound for contextual linear bandits.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-00826946
Contributor : Michal Valko <>
Submitted on : Tuesday, May 28, 2013 - 3:52:18 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Tuesday, September 3, 2013 - 9:52:58 AM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00826946, version 1

Citation

Michal Valko, Nathan Korda, Rémi Munos, Ilias Flaounas, Nello Cristianini. Finite-Time Analysis of Kernelised Contextual Bandits. Uncertainty in Artificial Intelligence, Jul 2013, Bellevue, United States. ⟨hal-00826946⟩

Share

Metrics

Record views

645

Files downloads

429