People


Emilie Kaufmann

Emilie Kaufmann
IndexInstitutionofficehomepagegroup
0 ■ InriaNoneNoneFormer members of the LINCS

Books And Theses

⇣ Analysis of bayesian and frequentist strategies for sequential resource allocation Analyse de stratégies bayésiennes et fréquentistes pour l'allocation séquentielle de ressources,
Emilie Kaufmann ■,
2014

Articles

⇣ Efficient Algorithms for Extreme Bandits,
Dorian Baudry, Yoan Russac, Emilie Kaufmann,
AISTATS 2022
⇣ ⇣ Optimal Thompson Sampling strategies for support-aware CVaR bandits,
Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric Maillard,
ICML 2021, Virtual, United States
⇣ ⇣ Fast active learning for pure exploration in reinforcement learning,
Pierre Menard, Omar Darwiche Domingues, Anders Jonsson, Emilie Kaufmann, Edouard Leurent, Michal Valko,
ICML 2021, Vienna, Austria
⇣ ⇣ A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces,
Omar Darwiche Domingues, Pierre Menard, Matteo Pirotta, Emilie Kaufmann, Michal Valko,
AISTATS 2021, San Diego / Virtual, United States
⇣ ⇣ Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited,
Omar Darwiche Domingues, Pierre Menard, Emilie Kaufmann, Michal Valko,
ALT 2021, Paris / Virtual, France
⇣ ⇣ Kernel-Based Reinforcement Learning: A Finite-Time Analysis,
Omar Darwiche Domingues, Pierre Menard, Matteo Pirotta, Emilie Kaufmann, Michal Valko,
ICML 2021, Vienna / Virtual, Austria
⇣ ⇣ Top-m identification for linear bandits,
Clemence Reda, Emilie Kaufmann, Andree Delahaye Duriez,
AISTATS 2021, Virtual, United States
⇣ ⇣ Adaptive Reward-Free Exploration,
Emilie Kaufmann, Pierre Menard, Omar Darwiche Domingues, Anders Jonsson, Edouard Leurent, Michal Valko,
ALT 2021, Paris, France
⇣ ⇣ Sub-sampling for Efficient Non-Parametric Bandit Exploration,
Dorian Baudry, Emilie Kaufmann, Odalric Ambrym Maillard,
NeurIPS 2020, Vancouver, Canada
⇣ ⇣ Planning in Markov Decision Processes with Gap-Dependent Sample Complexity,
Anders Jonsson, Emilie Kaufmann, Pierre Menard, Omar Darwiche Domingues, Edouard Leurent, Michal Valko,
NeurIPS 2020, Vancouver, France
⇣ ⇣ A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among Players,
Abbas Mehrabian, Etienne Boursier, Emilie Kaufmann, Vianney Perchet,
AISTATS 2020, Palermo, Italy
⇣ ⇣ Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling,
Cindy Trinh, Emilie Kaufmann, Claire Vernade, Richard Combes,
ALT 2020, San Diego, United States
⇣ ⇣ Fixed-confidence guarantees for Bayesian best-arm identification,
Xuedong Shang, Rianne De Heide, Pierre Menard, Emilie Kaufmann, Michal Valko,
AISTATS 2020, Palermo, Italy
⇣ Analyse non asymptotique d'un test séquentiel de détection de rupture et application aux bandits non stationnaires Non-asymptotic analysis of a sequential rupture detection test and its application to non-stationary bandits,
Lilian Besson, Emilie Kaufmann,
GRETSI 2019 - XXVIIème Colloque francophone de traitement du signal et des images 2019, Lille, France
⇣ A simple dynamic bandit algorithm for hyper-parameter tuning,
Xuedong Shang, Emilie Kaufmann, Michal Valko,
Workshop on Automated Machine Learning at International Conference on Machine Learning 2019, Long Beach, United States
⇣ General parallel optimization without a metric,
Xuedong Shang, Emilie Kaufmann, Michal Valko,
Algorithmic Learning Theory 2019, Chicago, United States
⇣ General parallel optimization a without metric,
Xuedong Shang, Emilie Kaufmann, Michal Valko,
ALT 2019
⇣ Adaptive black-box optimization got easier: HCT only needs local smoothness,
Xuedong Shang, Emilie Kaufmann, Michal Valko,
European Workshop on Reinforcement Learning 2018, Lille, France
⇣ ⇣ Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling,
Emilie Kaufmann, Wouter Koolen, Aurelien Garivier,
NeurIPS 2018, Montréal, Canada
⇣ ⇣ Corrupt Bandits for Preserving Local Privacy,
Pratik Gajane, Tanguy Urvoy, Emilie Kaufmann,
ALT 2018, Lanzarote, Spain
⇣ ⇣ Pure Exploration in Infinitely-Armed Bandit Models with Fixed-Confidence,
Maryam Aziz, Jesse Anderton, Emilie Kaufmann, Javed Aslam,
ALT 2018, Lanzarote, Spain
⇣ Multi-Player Bandits Revisited Modèles de Bandits Multi-Joueurs Revisités,
Lilian Besson, Emilie Kaufmann,
Algorithmic Learning Theory 2018, Lanzarote, Spain
⇣ Aggregation of Multi-Armed Bandits Learning Algorithms for Opportunistic Spectrum Access Agrégation d'algorithmes d'apprentissage pour les bandits multi-bras appliquée à l'accès opportuniste au spectre,
Lilian Besson, Emilie Kaufmann, Christophe Moy,
IEEE WCNC - IEEE Wireless Communications and Networking Conference 2018, Barcelona, Spain
⇣ {Multi-Player Bandits Revisited},
Lilian Besson, Emilie Kaufmann,
ALT 2018
⇣ Aggregation of multi-armed bandits learning algorithms for opportunistic spectrum access,
Lilian Besson, Emilie Kaufmann, Christophe Moy,
WCNC 2018
⇣ Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings Apprentissage de Bandit Multi-Bras dans les réseaux Internet des Objets: l'apprentissage est utile même dans des cas non-stationnaires,
Rémi Bonnefoi, Lilian Besson, Christophe Moy, Emilie Kaufmann, Jacques Palicot,
CROWNCOM 2017 - 12th EAI International Conference on Cognitive Radio Oriented Wireless Networks 2017, Lisbon, Portugal
⇣ ⇣ Monte-Carlo Tree Search by Best Arm Identification,
Emilie Kaufmann, Wouter Koolen,
NIPS 2017, Long Beach, United States
⇣ ⇣ Maximin Action Identification: A New Bandit Framework for Games,
Aurelien Garivier, Emilie Kaufmann, Wouter Koolen,
COLT 2016, New-York, United States
⇣ ⇣ On Explore-Then-Commit strategies,
Aurelien Garivier, Tor Lattimore, Emilie Kaufmann,
NIPS 2016, Barcelona, Spain
⇣ ⇣ Optimal Best Arm Identification with Fixed Confidence,
Aurelien Garivier, Emilie Kaufmann,
COLT 2016, New York, United States
⇣ ⇣ On the Complexity of A/B Testing,
Emilie Kaufmann ■, Olivier Cappe, Aurelien Garivier,
COLT 2014, Barcelona, Spain
⇣ Thompson Sampling for one-dimensial exponential family bandits,
Nathaniel Korda, Emilie Kaufmann, Rémi Munos,
NIPS 2013 - Neural Information Processing Systems Conference 2013, Lake Tahoe, United States
⇣ ⇣ Information Complexity in Bandit Subset Selection,
Emilie Kaufmann, Shivaram Kalyanakrishnan,
COLT 2013, Princeton, United States
⇣ Thompson sampling for one-dimensional exponential family bandits,
Nathaniel Korda, Emilie Kaufmann, Rémi Munos,
Advances in Neural Information Processing Systems 2013, United States
⇣ Thompson Sampling for 1-Dimensional Exponential Family Bandits,
Nathaniel Korda, Emilie Kaufmann, Remi Munos,
NIPS 2013
⇣ ⇣ Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis,
Emilie Kaufmann, Nathaniel Korda, Remi Munos,
ALT 2012, Lyon, France
⇣ ⇣ On Bayesian Upper Confidence Bounds for Bandit Problems,
Emilie Kaufmann, Olivier Cappe, Aurelien Garivier,
AISTATS 2012, La Palma, Iles Canaries, Spain

Journal articles

⇣ ⇣ Mixture Martingales Revisited with Applications to Sequential Tests and Confidence Intervals,
Emilie Kaufmann, Wouter Koolen,
Journal of Machine Learning Research 2021
⇣ Non-Asymptotic Sequential Tests for Overlapping Hypotheses and application to near optimal arm identification in bandit models,
Aurélien Garivier, Emilie Kaufmann,
Sequential Analysis 2021
⇣ ⇣ On Multi-Armed Bandit Designs for Dose-Finding Trials,
Maryam Aziz, Emilie Kaufmann, Marie Karelle Riviere,
Journal of Machine Learning Research 2021
⇣ Machine learning applications in drug development,
Clémence Réda, Emilie Kaufmann, Andrée Delahaye-Duriez,
Computational and Structural Biotechnology Journal 2020
⇣ ⇣ Asymptotically optimal algorithms for budgeted multiple play bandits,
Alexander Luedtke, Emilie Kaufmann, Antoine Chambaz,
Machine Learning 2019
⇣ On Bayesian index policies for sequential resource allocation,
Emilie Kaufmann,
Annals of Statistics 2018
⇣ ⇣ A spectral algorithm with additive clustering for the recovery of overlapping communities in networks,
Emilie Kaufmann, Thomas Bonald ■, Marc Lelarge ■,
Theoretical Computer Science 2018
⇣ ⇣ On the Complexity of Best-Arm Identification in Multi-Armed Bandit Models,
Emilie Kaufmann, Olivier Cappe, Aurelien Garivier,
Journal of Machine Learning Research 2016

Reports

⇣ Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPs,
Andrea Tirinzoni, Aymen Al Marjani, Emilie Kaufmann,
CoRR 2022
⇣ Near-Optimal Collaborative Learning in Bandits,
Clemence Reda, Sattar Vakili, Emilie Kaufmann,
CoRR 2022
⇣ Regret Bounds for Kernel-Based Reinforcement Learning,
Omar Darwiche Domingues, Pierre Menard, Matteo Pirotta, Emilie Kaufmann, Michal Valko,
CoRR 2020
⇣ Thompson Sampling for CVaR Bandits,
Dorian Baudry, Romain Gautron, Emilie Kaufmann, Odalric Ambrym Maillard,
CoRR 2020
⇣ New Algorithms for Multiplayer Bandits when Arm Means Vary Among Players,
Emilie Kaufmann, Abbas Mehrabian,
CoRR 2019
⇣ The Generalized Likelihood Ratio Test meets klUCB: an Improved Algorithm for Piece-Wise Non-Stationary Bandits,
Lilian Besson, Emilie Kaufmann,
CoRR 2019
⇣ On Multi-Armed Bandit Designs for Phase I Clinical Trials,
Maryam Aziz, Emilie Kaufmann, Marie Karelle Riviere,
CoRR 2019
⇣ What Doubling Tricks Can and Can't Do for Multi-Armed Bandits,
Lilian Besson, Emilie Kaufmann,
CoRR 2018
⇣ Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settings,
Remi Bonnefoi, Lilian Besson, Christophe Moy, Emilie Kaufmann, Jacques Palicot,
CoRR 2018
⇣ ⇣ Learning the distribution with largest mean: two bandit frameworks,
Emilie Kaufmann, Aurelien Garivier,
ESAIM: Proceedings and Surveys 2017
⇣ Corrupt Bandits for Privacy Preserving Input,
Pratik Gajane, Tanguy Urvoy, Emilie Kaufmann,
CoRR 2017
⇣ Multi-Player Bandits Models Revisited,
Lilian Besson, Emilie Kaufmann,
CoRR 2017
⇣ Asymptotically Optimal Algorithms for Multiple Play Bandits with Partial Feedback,
Alexander Luedtke, Emilie Kaufmann, Antoine Chambaz,
CoRR 2016
⇣ Thompson Sampling: An Optimal Finite Time Analysis,
Emilie Kaufmann, Nathaniel Korda, Remi Munos,
CoRR 2012

Misc

⇣ Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits,
Lilian Besson, Emilie Kaufmann, Odalric-Ambrym Maillard, Julien Seznec,
2020
⇣ What Doubling Tricks Can and Can't Do for Multi-Armed Bandits Ce que peuvent et ne peuvent pas faire les astuces de doublement pour les bandits multi-bras,
Lilian Besson, Emilie Kaufmann,
2018