Online learning with Erdős-Rényi side-observation graphs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Online learning with Erdős-Rényi side-observation graphs

Tomáš Kocák
  • Function : Author
  • PersonId : 955512
Michal Valko

Abstract

We consider adversarial multi-armed bandit problems where the learner is allowed to observe losses of a number of arms beside the arm that it actually chose. We study the case where all non-chosen arms reveal their loss with an unknown probability rt, independently of each other and the action of the learner. Moreover, we allow rt to change in every round t, which rules out the possibility of estimating rt by a well-concentrated sample average. We propose an algorithm which operates under the assumption that rt is large enough to warrant at least one side observation with high probability. We show that after T rounds in a bandit problem with N arms, the expected regret of our algorithm is of order O(sqrt(sum(t=1)T (1/rt) log N )), given that rt less than log T / (2N-2) for all t. All our bounds are within logarithmic factors of the best achievable performance of any algorithm that is even allowed to know exact values of rt.
Fichier principal
Vignette du fichier
kocak2016onlinea.pdf (326.76 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01320588 , version 1 (24-05-2016)

Identifiers

  • HAL Id : hal-01320588 , version 1

Cite

Tomáš Kocák, Gergely Neu, Michal Valko. Online learning with Erdős-Rényi side-observation graphs. Uncertainty in Artificial Intelligence, Jun 2016, New York City, United States. ⟨hal-01320588⟩
288 View
372 Download

Share

Gmail Facebook X LinkedIn More