AG
Aurélien Garivier
cs.LGstat.MLmath.STstat.THcs.AImath.PRmath.OCcs.DScs.ITmath.IT
On Valency
published · living versionsW_73bg9ucs·v1 · currentpublished
W_4gh879ma·v1published
W_s96vzvbn·v1published
W_btw9qywv·v1published
W_gfzjbtxd·v1published
Preprints & journals
62 papers in the corpus · 2008–2026On Minimum Divergence for Distribution Reconstruction2610.21872v1 · Justin Bec, Thomas Le Corre, Aur'elien Garivier2026 · 0 citationsarXiv
EVaR-Optimal Arm Identification in Bandits2510.04728v1 · Mehrasa Ahmadipour, Aur'elien Garivier2025 · 0 citationsarXiv
Efficient Risk-sensitive Planning via Entropic Risk Measures2502.20423v2 · Alexandre Marthe (ENS de Lyon, UMPA-ENSL), Samuel Bounan et al.2025 · 0 citationsarXiv
Identifying the Best Transition Law2502.12227v1 · Mehrasa Ahmadipour, 'elise Crepon, Aur'elien Garivier2025 · 0 citationsarXiv
Sequential Learning of the Pareto Front for Multi-objective Bandits2501.17513v1 · Elise Cr'epon (UMPA-ENSL), Aur'elien Garivier (UMPA-ENSL), Wouter M Koolen (CWI)2025 · 1 citationProceedings of Machine Learning Research, 2024, Proceedings of The 27th International Conference on Artificial Intelligence and Statistics, PMLR (238), pp.3583--3591
On Sparsity and Sub-Gaussianity in the Johnson-Lindenstrauss Lemma2409.06275v2 · Aur'elien Garivier (UMPA-ENSL, MC2), Emmanuel Pilliat (UMPA-ENSL)2024 · 0 citationsarXiv
Beyond Average Return in Markov Decision Processes2310.20266v2 · Alexandre Marthe (ENS de Lyon, UMPA-ENSL), Aur'elien Garivier (UMPA-ENSL (MC2)) et al.2023 · 0 citationsarXiv
About the Cost of Central Privacy in Density Estimation2306.14535v4 · Cl'ement Lalanne (ENS de Lyon, OCKHAM), Aur'elien Garivier (UMPA-ENSL et al.2023 · 0 citationsarXiv
Quantum Channel Certification with Incoherent Strategies2303.01188v2 · Omar Fawzi, Nicolas Flammarion, Aur'elien Garivier et al.2023 · 1 citationProceedings of Thirty Sixth Conference on Learning Theory, PMLR 195:1822-1884, 2023
Private Statistical Estimation of Many Quantiles2302.06943v3 · Cl'ement Lalanne (ENS de Lyon, DANTE, OCKHAM) et al.2023 · 0 citationsICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honolulu, United States
Stochastic Direct Search Method for Blind Resource Allocation2210.05222v2 · Juliette Achddou (PSL, DI-ENS), Olivier Cappe et al.2022 · 0 citationsTransactions on Machine Learning Research Journal, 2024
On the Statistical Complexity of Estimation and Testing under Privacy Constraints2210.02215v3 · Cl'ement Lalanne (DANTE, OCKHAM), Aur'elien Garivier (UMPA-ENSL) et al.2022 · 2 citationsTransactions on Machine Learning Research Journal, 2023
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits2210.00895v2 · Antoine Barrier (UMPA-ENSL, LMO, CELESTE) et al.2022 · 3 citationsALT 2023 - The 34th International Conference on Algorithmic Learning Theory, Feb 2023, Singapour, Singapore
Sequential algorithms for testing identity and closeness of distributions2205.06069v1 · Omar Fawzi, Nicolas Flammarion, Aur'elien Garivier et al.2022 · 1 citationarXiv
Private Quantiles Estimation in the Presence of Atoms2202.08969v2 · Cl'ement S'ebastien Lalanne (DANTE), Cl'ement Gastaud, Nicolas Grislain et al.2022 · 0 citationsarXiv
On the complexity of All -Best Arms Identification2202.06280v2 · Aymen Al Marjani, Tom'as Koc'ak, Aur'elien Garivier2022 · 2 citationsarXiv
A/B/n Testing with Control in the Presence of Subpopulations2110.15573v1 · Yoan Russac, Christina Katsimerou, Dennis Bohle et al.2021 · 9 citationsNeurIPS 2021, Dec 2021, Virtual, France
Fast Rate Learning in Stochastic First Price Bidding2107.01835v2 · Juliette Achddou (DI-ENS, VALDA ), Olivier Capp'e (VALDA et al.2021 · 3 citationsACML 2021 - Proceedings of Machine Learning Research 157, 2021, Nov 2021, SIngapore, Singapore
Navigating to the Best Policy in Markov Decision Processes2106.02847v2 · Aymen Al Marjani, Aur'elien Garivier, Alexandre Proutiere2021 · 5 citationsarXiv
A Non-asymptotic Approach to Best-Arm Identification for Gaussian Bandits2105.12978v2 · Antoine Barrier (UMPA-ENSL, LMO), Aur'elien Garivier (UMPA-ENSL) et al.2021 · 2 citations25th International Conference on Artificial Intelligence and Statistics (AISTATS) 2022, Mar 2022, Valencia, Spain
Efficient Algorithms for Stochastic Repeated Second-price Auctions2011.05072v2 · Juliette Achddou (VALDA), Olivier Capp'e (VALDA), Aur'elien Garivier (UMPA-ENSL)2020 · 2 citationsALT 2021, Mar 2021, Paris, France
Self-Concordant Analysis of Generalized Linear Bandits with Forgetting2011.00819v2 · Yoan Russac, Louis Faury, Olivier Capp'e (DI-ENS et al.2020 · 3 citationsAISTATS 2021 - International Conference on Artificial Intelligence and Statistics, Apr 2021, San Diego / Virtual, United States
Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening2007.03373v2 · Louis B'ethune, Yacouba Kaloga, Pierre Borgnat et al.2020 · 5 citationsarXiv
Best Arm Identification in Spectral Bandits2005.09841v1 · Tom'as Koc'ak, Aur'elien Garivier2020 · 5 citationsarXiv
Algorithms for Non-Stationary Generalized Linear Bandits2003.10113v1 · Yoan Russac (DI-ENS), Olivier Capp'e (DI-ENS), Aur'elien Garivier (UMPA-ENSL)2020 · 9 citationsarXiv
Non-Asymptotic Sequential Tests for Overlapping Hypotheses and application to near optimal arm identification in bandit models1905.03495v2 · Aur'elien Garivier (UMPA-ENSL, MC2), Emilie Kaufmann2019 · 2 citationsSequential Analysis, Taylor \& Francis, 2021
X-Armed Bandits: Optimizing Quantiles, CVaR and Other Risks1904.08205v3 · L'eonard Torossian, Aur'elien Garivier, Victor Picheny2019 · 11 citationsarXiv
A Review on Quantile Regression for Stochastic Computer Experiments1901.07874v4 · L'eonard Torossian, Victor Picheny, Robert Faivre et al.2019 · 23 citationsarXiv
Can everyday AI be ethical. Fairness of Machine Learning Algorithms1810.01729v1 · Philippe Besse, Celine Castets-Renard, Aurelien Garivier et al.2018 · 2 citationsarXiv
Optimization of a SSP's Header Bidding Strategy using Thompson Sampling1807.03299v1 · Gr'egoire Jauvion, Nicolas Grislain, Pascal Sielenou Dkengne (IMT) et al.2018 · 19 citationsThe 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug 2018, London, United Kingdom
Sequential Test for the Lowest Mean: From Thompson to Murphy Sampling1806.00973v1 · Emilie Kaufmann, Wouter Koolen (CWI), Aurelien Garivier (IMT)2018 · 14 citationsarXiv
KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints1805.05071v3 · Aur'elien Garivier, H'edi Hadiji, Pierre Menard et al.2018 · 10 citationsarXiv
Profitable Bandits1805.02908v1 · Mastane Achab, Stephan Cl'emencon, Aur'elien Garivier2018 · 2 citationsarXiv
Thresholding Bandit for Dose-ranging: The Impact of Monotonicity1711.04454v2 · Aur'elien Garivier (IMT), Pierre M'enard (IMT), Laurent Rossi (IMT) et al.2017 · 11 citationsarXiv
A note on perfect simulation for exponential random graph models1710.00873v1 · Andressa Cerqueira, Aur'elien Garivier, Florencia Leonardi2017 · 0 citationsarXiv
Max K-armed bandit: On the ExtremeHunter algorithm and beyond1707.08820v1 · Mastane Achab, Stephan Cl'emencon, Aur'elien Garivier et al.2017 · 58 citationsarXiv
A minimax and asymptotically optimal algorithm for stochastic bandits1702.07211v2 · Pierre M'enard, Aur'elien Garivier2017 · 71 citationsAlgorithmic Learning Theory, Springer, 2017, 2017 Algorithmic Learning Theory Conference 76
Learning the distribution with largest mean: two bandit frameworks1702.00001v3 · Emilie Kaufmann, Aur'elien Garivier (IMT)2017 · 15 citationsESAIM: Proceedings and Surveys, EDP Sciences, A Para{\^i}tre, 2017, pp.1 - 10
On Explore-Then-Commit Strategies1605.08988v2 · Aur'elien Garivier (IMT), Emilie Kaufmann, Tor Lattimore2016 · 109 citationsarXiv
Explore First, Exploit Next: The True Shape of Regret in Bandit Problems1602.07182v3 · Aur'elien Garivier (IMT), Pierre M'enard (IMT), Gilles Stoltz (GREGH)2016 · 16 citationsarXiv
Optimal Best Arm Identification with Fixed Confidence1602.04589v2 · Aur'elien Garivier (IMT), Emilie Kaufmann (CRIStAL, SEQUEL)2016 · 115 citationsarXivon Valency
Maximin Action Identification: A New Bandit Framework for Games1602.04676v1 · Aur'elien Garivier (IMT), Emilie Kaufmann (CRIStAL, SEQUEL) et al.2016 · 5 citationsarXiv
Conditional quantile sequential estimation for stochastic codes1508.06505v6 · Tatiana Labopin-Richard (IMT), Fabrice Gamboa (IMT), Aur'elien Garivier (UMPA-ENSL et al.2015 · 0 citationsarXiv
On the Complexity of Best Arm Identification in Multi-Armed Bandit Models1407.4443v2 · Emilie Kaufmann (SEQUEL, LTCI), Olivier Capp'e (LTCI) et al.2014 · 704 citationsJournal of Machine Learning Research, Journal of Machine Learning Research, 2016, 17, pp.1-42on Valency
Bregman superquantiles. Estimation methods and applications1405.6677v4 · Tatiana Labopin-Richard (IMT), Fabrice Gamboa (IMT), Aur'elien Garivier (IMT) et al.2014 · 5 citationsarXiv
On the Complexity of A/B Testing1405.3224v2 · Emilie Kaufmann (LTCI), Olivier Capp'e (LTCI), Aur'elien Garivier (IMT)2014 · 12 citationsConference on Learning Theory, Jun 2014, Barcelona, Spain. JMLR: Workshop and Conference Proceedings, 35, pp.461-481
Big Data Analytics - Retour vers le Futur 3; De Statisticien à Data Scientist1403.3758v3 · Philippe Besse (IMT), Aur'elien Garivier (IMT), Jean-Michel Loubes (IMT)2014 · 4 citationsarXiv
Informational Confidence Bounds for Self-Normalized Averages and Applications1309.3376v1 · Aur'elien Garivier2013 · 74 citations2013 IEEE Information Theory Workshop p.489-493on Valency
Kullback-Leibler upper confidence bounds for optimal sequential allocation1210.1136v4 · Olivier Capp'e, Aur'elien Garivier, Odalric-Ambrym Maillard et al.2012 · 307 citationsAnnals of Statistics 2013, Vol. 41, No. 3, 1516-1541
Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality1207.5259v3 · Sebastien Bubeck, Damien Ernst, Aurelien Garivier2012 · 18 citationsarXiv
Career total: 136 works. 62 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.