Skip to Main content Skip to Navigation
Conference papers

Online combinatorial optimization with stochastic decision sets and adversarial losses

Gergely Neu 1 Michal Valko 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : Most work on sequential learning assumes a fixed set of actions that are available all the time. However, in practice, actions can consist of picking subsets of readings from sensors that may break from time to time, road segments that can be blocked or goods that are out of stock. In this paper we study learning algorithms that are able to deal with stochastic availability of such unreliable composite actions. We propose and analyze algorithms based on the Follow-The-Perturbed-Leader prediction method for several learning settings differing in the feedback provided to the learner. Our algorithms rely on a novel loss estimation technique that we call Counting Asleep Times. We deliver regret bounds for our algorithms for the previously studied full information and (semi-)bandit settings, as well as a natural middle point between the two that we call the restricted information setting. A special consequence of our results is a significant improvement of the best known performance guarantees achieved by an efficient algorithm for the sleeping bandit problem with stochastic availability. Finally, we evaluate our algorithms empirically and show their improvement over the known approaches.
Document type :
Conference papers
Complete list of metadata

Cited literature [17 references]  Display  Hide  Download
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Monday, November 3, 2014 - 1:33:07 PM
Last modification on : Saturday, December 18, 2021 - 3:05:14 AM


Files produced by the author(s)


  • HAL Id : hal-01079355, version 2


Gergely Neu, Michal Valko. Online combinatorial optimization with stochastic decision sets and adversarial losses. Neural Information Processing Systems, Dec 2014, Montréal, Canada. ⟨hal-01079355v2⟩



Les métriques sont temporairement indisponibles