22 citations
- Afterschool AllianceUS2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Centre de Recherche en InformatiqueFR1 paper
- Centre de Recherche en Informatique, Signal et Automatique de LilleFR1 paper
- Centrum Wiskunde & InformaticaNL1 paper
- Cristal (United Kingdom)GB1 paper
- Criteo (France)FR1 paper
- Laboratoire Traitement et Communication de l’InformationFR1 paper
- Renault (France)FR1 paper
- Université de LilleFR1 paper
7 papers
Sub-sampling for Efficient Non-Parametric Bandit Exploration
Dorian Baudry, Emilie Kaufmann, Odalric-Ambrym Maillard
In this paper we propose the first multi-armed bandit algorithm based on re-sampling that achieves asymptotically optimal regret simultaneously for different families of arms (name…
Optimal Strategies for Graph-Structured Bandits
Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
We study a structured variant of the multi-armed bandit problem specified by a set of Bernoulli distributions with mean…
Forced-exploration free Strategies for Unimodal Bandits
Hassan Saber, Pierre Ménard, Odalric-Ambrym Maillard
We consider a multi-armed bandit problem specified by a set of Gaussian or Bernoulli distributions endowed with a unimodal structure. Although this problem has been addressed in th…
Approximate Robust Control of Uncertain Dynamical Systems
Edouard Leurent, Yann Blanco, Denis Efimov +1
This work studies the design of safe control policies for large-scale non-linear systems operating in uncertain environments. In such a case, the robust control framework is a prin…
Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals
Emilie Kaufmann, Wouter Koolen
This paper presents new deviation inequalities that are valid uniformly in time under adaptive sampling in a multi-armed bandit model. The deviations are measured using the Kullbac…
Recurrent Neural Networks for Long and Short-Term Sequential Recommendation
Kiewan Villatel, Elena Smirnova, Jérémie Mary +1
Recommender systems objectives can be broadly characterized as modeling user preferences over short-or long-term time horizon. A large body of previous research studied long-term r…