From the archives

Keyword: Bandit Problems

Historical material. Affiliations, schedules and roles on this page describe their original context.

Publication in Journal - May, 2019 Non-Asymptotic Sequential Tests for Overlapping Hypotheses and application to near optimal arm identification in bandit models Publication in Conference - April, 2019 X-Armed Bandits: Optimizing Quantiles and Other Risks Publication in Conference - December, 2018 Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling Neural Information Processing Systems Presentation - November, 2018 Complexity of Sequential Decision Problems ENS Lyon, Théminaire Théminaire de l'ENS Lyon Publication in Conference - November, 2018 Profitable Bandits Asian Conference on Machine Learning Presentation - October, 2018 Introduction à certains problèmes de décisions séquentielles Rencontre des Statisticiens Lyonnais (RSL), Campus de La Doua Presentation - October, 2018 Comment les maths peuvent-elles aider les machines à apprendre ? ENS Lyon, Journée de rentrée de l'UMPA Publication in Journal - September, 2018 Explore First, Exploit Next: The True Shape of Regret in Bandit Problems Mathematics of Operations Research Publication in Conference - August, 2018 Optimization of a SSP's Header Bidding Strategy using Thompson Sampling Special Interest Group on Knowledge Discovery and Data Mining Presentation - May, 2018 Missing Mass, and Optimal Discovery ENS Lyon Laboratoire de l'Informatique du Parallélisme Publication in Journal - May, 2018 KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints Presentation - April, 2018 Minimisation du regret pour des bandits non-paramétriques grâce à la méthode de la vraisemblance empirique ENS Lyon Séminaire de l'UMPA Publication in Journal - December, 2017 Learning the distribution with largest mean: two bandit frameworks ESAIM: Proceedings and Surveys Publication in Conference - October, 2017 Thresholding Bandit for Dose-ranging: The Impact of Monotonicity Publication in Conference - October, 2017 A minimax and asymptotically optimal algorithm for stochastic bandits Algorithmic Learning Theory Publication in Conference - September, 2017 Max K-armed bandits: On the ExtremeHunter algorithm and beyond European Conference on Machine Learning Presentation - July, 2017 The Complexity of Best-Arm Identification Barcelona, FoCM2017 Workshop on Stochastic Computation (archive lookup) Publication in Journal - March, 2017 Diversified Bandit: the k-diversified Multiple-Play Recommendation Algorithm Publication in Journal - March, 2017 Les systèmes de recommandations en ligne Les Big Data à Découvert, Editions CNRS Publication in Conference - December, 2016 On Explore-Then-Commit Strategies Neural Information Processing Systems Presentation - August, 2016 Sur la complexité de l'identification du meilleur bras sous contrainte de risque dans un modèle de bandits Grenoble, Journées MAS 2016 Journées MAS 2016 Publication in Conference - July, 2016 Algorithme de bandit et obsolescence : un modèle pour la recommandation Conférence Francophone sur l'Apprentissage Automatique Presentation - June, 2016 Optimal Best Arm Identification with Fixed Confidence New York COLT 2016 (archive lookup), videolectures Presentation - June, 2016 On the Complexity of Best Arm Identification with Fixed Confidence Séminaire Pluridisciplinaire d'Optimisation de Toulouse SPOT (archive lookup) Publication in Conference - June, 2016 Optimal Best Arm Identification with Fixed Confidence Conference On Learning Theory Publication in Conference - June, 2016 Maximin Action Identification: A New Bandit Framework for Games Conference On Learning Theory Presentation - May, 2016 Recent advances in the understanding of bandit models Grenoble, rencontres ANR ALICIA Presentation - May, 2016 De l'intérêt des méthodes séquentielles (une introduction) Toulouse, rencontres ANR SPADRO Presentation - March, 2016 Sequential Optimization and Computer Experiments Toulouse MASCOT-NUM 2016 Meeting Presentation - January, 2016 Optimal Discovery with Probabilistic Expert Advice Lancaster University, UK Multi-armed Bandit Workshop 2016 at STOR-i (archive lookup) Publication in Journal - January, 2016 On the Complexity of Best Arm Identification in Multi-Armed Bandit Models Journal of Machine Learning Research Presentation - June, 2015 Systèmes de recommandation et algorithmes de bandits: notebook ipython pour l'enseignement Lille, JDS 47èmes Journées de Statistique de la SFdS (archive lookup) Publication in Conference - May, 2015 A Multiple-play Bandit Algorithm Applies to Recommender Systems Florida Artificial Intelligence Research Society Conference Publication in Conference - March, 2015 Algorithmes de bandit pour les systèmes de recommandation : le cas de multiples recommandations simultanées Conférence en Recherche d’Information et Applications Presentation - March, 2015 On the Complexity of Best Arm Identification in Multi-Armed Bandit Models Berkeley Information Theory, Learning and Big Data Workshop, Simons Institute (archive lookup), youtube presentation Publication in Journal - February, 2015 Algorithmes de bandits pour la recommandation à tirages multiples Document numérique (Hermès) Presentation - October, 2014 Bandits for Exploration: Best Arm Identification and Discovery with Probabilistic Experts Imperial College, Multi-armed bandits meeting http://wwwf.imperial.ac.uk/~amijatov/IP/lps.php Presentation - October, 2014 Allocation dynamique de ressources et modèles de bandits Toulouse School of Economics, UT1 séminaire MAD Presentation - September, 2014 Allocation dynamique de ressources et modèles de bandits INRA Toulouse Séminaire MIAT (archive lookup) Presentation - June, 2014 Empirical Likelihood Upper Confidence Bounds For Bandit Models Barcelona, Journées Statistiques du Sud 2014 7èmes Journées Statistiques du Sud Publication in Conference - June, 2014 On the Complexity of A/B Testing Conference On Learning Theory Presentation - April, 2014 Empirical Likelihood for Optimistic Algorithms in Dynamic Resource Allocation Paris X Nanterre ANR SPADRO kick-off meeting Presentation - April, 2014 Optimistic Solutions for Dynamic Resource Allocation Paris (AgroParisTech) StatLearn 2014 Presentation - December, 2013 Optimal Discovery with Probabilistic Expert Advice: Finite Time Analysis and Macroscopic Optimality CIRM, Rencontres de Statistique Mathématique "Mathematical Statistics with Applications in Mind" site web, Programme de la rencontre Presentation - September, 2013 Informational Confidence Bounds for Self-Normalized Averages and Applications Seville (Spain) 2013 IEEE Information Theory Workshop Publication in Conference - September, 2013 Informational Confidence Bounds for Self-Normalized Averages and Applications IEEE Information Theory Workshop Publication in Journal - June, 2013 Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation Annals of Statistics Presentation - May, 2013 Quelques idées sur les problèmes de bandits Mini-colloque LPT-IMT 2013, Séminaire de l'équipe GEPETTO (LAAS Toulouse) (archive lookup) Presentation - March, 2013 Dynamic resource allocation as an estimation problem Fête Parisienne in Computation, Inference and Optimization in IHES (Bures sur Yvette) (archive lookup) Presentation - February, 2013 Problèmes de décisions séquentielles plusieurs exposés dans le cadre du groupe de travail co-organisé avec Sébastien Gerchinovitz à l'IMT Publication in Journal - February, 2013 Optimal Discovery with Probabilistic Expert Advice: Finite Time Analysis and Macroscopic Optimality Journal of Machine Learning Research Publication in Conference - December, 2012 Optimal Discovery with Probabilistic Expert Advice IEEE Conference on Decision and Control Presentation - November, 2012 Extraction d'information en grandes dimensions & allocation dynamique de ressources avec Jean-Michel Loubès Séminaire FREMIT (archive lookup) Presentation - July, 2012 Problèmes de bandits et estimation Séminaire de recherche du département TSI de Telecom ParisTech Publication in Conference - April, 2012 On Bayesian Upper Confidence Bounds for Bandit Problems International Conference on Artificial Intelligence and Statistics Presentation - January, 2012 Apprentissage par renforcement et déviations auto-normalisées Séminaire de statistiques de Toulouse (archive lookup), Séminaire parisien Presentation - December, 2011 Exploration optimale à l'aide d'experts probabilistes Séminaire du CMAP (Ecole Polytechnique, Palaiseau) Presentation - November, 2011 Analyses d'algorithmes pour l'estimation et l'optimisation stochastiques Soutenance d'habilitation à diriger des recherches (HDR), Orsay Other Publication - November, 2011 Analyse d'algorithmes pour l'estimation et l'optimisation stochastiques Presentation - October, 2011 On Upper-Confidence Bound Policies for Non-stationary Bandit Problems ALT 2011 (Espoo, Finlande) Publication in Conference - October, 2011 On Upper-Confidence Bound Policies for Non-stationary Bandit Problems Algorithmic Learning Theory Presentation - July, 2011 The KL-UCB for bounded bandit problems, and beyond Budapest, Hongrie COLT 2011, videolectures Publication in Conference - July, 2011 The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond Conference On Learning Theory Presentation - June, 2011 L'algorithme KL-UBC pour les bandits bornés, et au delà, I3M (Montpellier) puis ENGREF, groupe de travail prévision, Séminaire du I3M de Montpellier, puis ENGREF slideshare Publication in Conference - December, 2010 Parametric Bandits: The Generalized Linear Case Neural Information Processing Systems Presentation - October, 2010 Reinforcement Learning and Self-Normalized Deviation Bounds Séminaire du Numec, USP, Sao Paulo Publication in Conference - June, 2010 Bandits contextuels: apprentissage par renforcement dans les modèles linéaires généralisés Journées Francophones Planification, Décision, et Apprentissage pour la conduite de systèmes Presentation - March, 2010 Présentation de l'équipe et de l'apprentissage par renforcement Evaluation AERES de l'équipe STA du LTCI à Telecom ParisTech, avec François Roueff Presentation - June, 2008 Stratégies UCB en environnement non stationnaire European Workshop on Reinforcement Learning in Lille