
Emilie Kaufmann
66
Documents
Publications
10
9
6
6
5
5
4
4
4
4
4
4
3
3
3
3
3
3
2
2
2
2
2
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
1
22
20
8
8
7
5
4
2
2
2
2
1
1
1
1
1
4
4
1
36
36
24
20
5
4
4
2
1
Publications
|
Best-Arm Identification in Unimodal BanditsAISTATS 2025 - 28th International Conference on Artificial Intelligence and Statistics, May 2025, Phuket, Thailand
Communication dans un congrès
hal-05125233
v1
|
|
Pareto Set Identification With Posterior SamplingAISTATS 2025 - 28th International Conference on Artificial In- telligence and Statistic, May 2025, Phuket, Thailand
Communication dans un congrès
hal-05125257
v1
|
|
Bandit Pareto Set Identification in a Multi-Output Linear ModelAISTATS 2025 - 28th International Conference on Artificial Intelligence and Statistics, May 2025, Phuket, Thailand
Communication dans un congrès
hal-05125311
v1
|
|
Constrained Pareto Set Identification with Bandit FeedbackICML 2025 - 42nd International Conference on Machine Learning, Jul 2025, Vancouver, Canada
Communication dans un congrès
hal-05125339
v1
|
|
Bandit Pareto Set Identification: the Fixed Budget SettingAISTATS 2024 - 27th International Conference on Artifi- cial Intelligence and Statistics, May 2024, Valencia, Spain
Communication dans un congrès
hal-04877368
v1
|
|
Optimal Multi-Fidelity Best-Arm IdentificationAdvances in Neural Information Processing Systems (NeurIPS), Dec 2024, Vancouver (BC), Canada
Communication dans un congrès
hal-04811199
v1
|
|
Finding good policies in average-reward Markov Decision Processes without prior knowledgeNeurIPS, Dec 2024, Vancouver (Canada), Canada
Communication dans un congrès
hal-04809429
v1
|
|
Power Mean Estimation in Stochastic Monte-Carlo Tree SearchUncertainty in Artificial Intelligence, Jul 2024, Barcelona, Spain
Communication dans un congrès
hal-04714124
v1
|
|
Dealing with Unknown Variances in Best-Arm IdentificationAlgorithmic Learning Theory (ALT), Feb 2023, Singapore (SG), Singapore
Communication dans un congrès
hal-04306221
v1
|
|
An ε-Best-Arm Identification Algorithm for Fixed-Confidence and BeyondAdvances in Neural Information Processing Systems (NeurIPS), Dec 2023, New Orleans, United States
Communication dans un congrès
hal-04306214
v1
|
|
Active Coverage for PAC Reinforcement LearningConference on Learning Theory 2023, Jul 2023, Bangalore, India
Communication dans un congrès
hal-04215441
v1
|
|
Optimistic PAC Reinforcement Learning: the Instance-Dependent ViewAlgorithmic Learning Theory (ALT), Feb 2023, Singapore (SG), Singapore
Communication dans un congrès
hal-04306228
v1
|
|
Adaptive Algorithms for Relaxed Pareto Set IdentificationNeurIPS 2023 - 37th Conference on Neural Information Processing Systems, Dec 2023, La Nouvelle Orléans, LA, United States
Communication dans un congrès
hal-04306210
v1
|
|
Near-Optimal Collaborative Learning in BanditsNeurIPS 2022 - 36th Conference on Neural Information Processing System, Dec 2022, New Orleans, United States
Communication dans un congrès
hal-03825099
v1
|
|
Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPsEWRL 2022 - European Workshop on Reinforcement Learning, Sep 2022, Milan, Italy
Communication dans un congrès
hal-03767412
v1
|
|
Top Two Algorithms RevisitedNeurIPS 2022 - 36th Conference on Neural Information Processing System, Nov 2022, New Orleans, United States
Communication dans un congrès
hal-03825103
v1
|
|
Efficient Algorithms for Extreme BanditsInternational conference on Artificial Intelligence and Statistics (AISTATS), Mar 2022, Virtual Conference, Spain
Communication dans un congrès
hal-03741302
v1
|
|
Near Instance-Optimal PAC Reinforcement Learning for Deterministic MDPsNeurIPS 2022 - 36th Conference on Neural Information Processing System, Nov 2022, New Orleans, United States
Communication dans un congrès
hal-03825101
v1
|
|
Optimistic PAC Reinforcement Learning: the Instance-Dependent ViewEWRL 2022 - European Workshop on Reinforcement Learning, Sep 2022, Milan, Italy
Communication dans un congrès
hal-03767409
v1
|
|
Episodic reinforcement learning in finite MDPs: Minimax lower bounds revisitedAlgorithmic Learning Theory, Mar 2021, Paris / Virtual, France
Communication dans un congrès
hal-03289004
v1
|
|
Kernel-based reinforcement Learning: A finite-time analysisInternational Conference on Machine Learning, Jul 2021, Vienna / Virtual, Austria
Communication dans un congrès
hal-02541790
v2
|
|
Fast active learning for pure exploration in reinforcement learningInternational Conference on Machine Learning, Jul 2021, Vienna, Austria
Communication dans un congrès
hal-02906985
v3
|
|
Optimal Thompson Sampling strategies for support-aware CVaR bandits38th International Conference on Machine Learning, Jul 2021, Virtual, United States
Communication dans un congrès
hal-03447244
v1
|
|
A kernel-based approach to non-stationary reinforcement learning in metric spacesInternational Conference on Artificial Intelligence and Statistics, Apr 2021, San Diego / Virtual, United States
Communication dans un congrès
hal-03289026
v1
|
|
Adaptive reward-free explorationAlgorithmic Learning Theory, 2021, Paris, France
Communication dans un congrès
hal-02864574
v1
|
|
Top-m identification for linear banditsProceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS), 2021, Virtual, United States
Communication dans un congrès
hal-03172145
v1
|
|
Solving Bernoulli Rank-One Bandits with Unimodal Thompson SamplingALT 2020 - 31st International Conference on Algorithmic Learning Theory, Feb 2020, San Diego, United States. pp.1 - 28
Communication dans un congrès
hal-02396943
v2
|
|
Fixed-confidence guarantees for Bayesian best-arm identificationInternational Conference on Artificial Intelligence and Statistics, 2020, Palermo, Italy
Communication dans un congrès
hal-02330187
v2
|
|
A Practical Algorithm for Multiplayer Bandits when Arm Means Vary Among PlayersAISTATS 2020 - 23rd International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo, Italy
Communication dans un congrès
hal-02006069
v3
|
|
Planning in Markov Decision Processes with Gap-Dependent Sample ComplexityNeural Information Processing Systems, 2020, Vancouver, France
Communication dans un congrès
hal-02863486
v2
|
|
Sub-sampling for Efficient Non-Parametric Bandit ExplorationNeurIPS 2020, Dec 2020, Vancouver, Canada
Communication dans un congrès
hal-02977552
v1
|
|
A simple dynamic bandit algorithm for hyper-parameter tuningWorkshop on Automated Machine Learning at International Conference on Machine Learning, AutoML@ICML 2019 - 6th ICML Workshop on Automated Machine Learning, Jun 2019, Long Beach, United States
Communication dans un congrès
hal-02145200
v1
|
|
Analyse non asymptotique d'un test séquentiel de détection de rupture et application aux bandits non stationnairesGRETSI 2019 - XXVIIème Colloque francophone de traitement du signal et des images, Aug 2019, Lille, France
Communication dans un congrès
hal-02152243
v1
|
|
General parallel optimization without a metricAlgorithmic Learning Theory, 2019, Chicago, United States
Communication dans un congrès
hal-02047225
v2
|
|
Multi-Armed Bandit Learning in IoT Networks: Learning helps even in non-stationary settingsCROWNCOM 2017 - 12th EAI International Conference on Cognitive Radio Oriented Wireless Networks, Sep 2017, Lisbon, Portugal. pp.173-185, ⟨10.1007/978-3-319-76207-4_15⟩
Communication dans un congrès
hal-01575419
v2
|
|
Corrupt Bandits for Preserving Local PrivacyALT 2018 - Algorithmic Learning Theory, Apr 2018, Lanzarote, Spain
Communication dans un congrès
hal-01757297
v1
|
|
Sequential Test for the Lowest Mean: From Thompson to Murphy SamplingAdvances in Neural Information Processing Systems (NIPS), Dec 2018, Montréal, Canada
Communication dans un congrès
hal-01804581
v1
|
|
Adaptive black-box optimization got easier: HCT only needs local smoothnessEuropean Workshop on Reinforcement Learning, Oct 2018, Lille, France
Communication dans un congrès
hal-01874637
v1
|
|
Pure Exploration in Infinitely-Armed Bandit Models with Fixed-ConfidenceALT 2018 - Algorithmic Learning Theory, Apr 2018, Lanzarote, Spain
Communication dans un congrès
hal-01729969
v1
|
|
Multi-Player Bandits RevisitedAlgorithmic Learning Theory, Mehryar Mohri; Karthik Sridharan, Apr 2018, Lanzarote, Spain
Communication dans un congrès
hal-01629733
v2
|
|
Aggregation of Multi-Armed Bandits Learning Algorithms for Opportunistic Spectrum AccessIEEE WCNC - IEEE Wireless Communications and Networking Conference, Apr 2018, Barcelona, Spain. ⟨10.1109/wcnc.2018.8377070⟩
Communication dans un congrès
hal-01705292
v1
|
|
Monte-Carlo Tree Search by Best Arm IdentificationNIPS 2017 - 31st Annual Conference on Neural Information Processing Systems, Dec 2017, Long Beach, United States. pp.1-23
Communication dans un congrès
hal-01535907
v2
|
|
Maximin Action Identification: A New Bandit Framework for Games29th Annual Conference on Learning Theory (COLT), Jun 2016, New-York, United States
Communication dans un congrès
hal-01273842
v2
|
|
On Explore-Then-Commit StrategiesNIPS, Dec 2016, Barcelona, Spain
Communication dans un congrès
hal-01322906
v2
|
|
Optimal Best Arm Identification with Fixed Confidence29th Annual Conference on Learning Theory (COLT), Jun 2016, New York, United States
Communication dans un congrès
hal-01273838
v2
|
|
On the Complexity of A/B TestingConference on Learning Theory, Jun 2014, Barcelona, Spain. pp.461-481
Communication dans un congrès
hal-00990254
v2
|
Thompson Sampling for one-dimensial exponential family banditsNIPS 2013 - Neural Information Processing Systems Conference, Dec 2013, Lake Tahoe, United States
Communication dans un congrès
hal-02288407
v1
|
|
Information Complexity in Bandit Subset SelectionConference On Learning Theory, Jun 2013, Princeton, United States
Communication dans un congrès
hal-02288406
v1
|
|
|
Thompson sampling for one-dimensional exponential family banditsAdvances in Neural Information Processing Systems, 2013, United States
Communication dans un congrès
hal-00923683
v1
|
|
Thompson Sampling: An Asymptotically Optimal Finite Time AnalysisALT 2012 - International Conference on Algorithmic Learning Theory, Oct 2012, Lyon, France. pp.199-213, ⟨10.1007/978-3-642-34106-9_18⟩
Communication dans un congrès
hal-00830033
v1
|
Thompson Sampling : an asymptotically optimal finite time analysisInternational Conference on Algorithmic Learning Theory, Nov 2012, Lyon, France. pp.199-213
Communication dans un congrès
hal-02286442
v1
|
|
On Bayesian Upper Confidence Bounds for Bandit ProblemsInternational Conference on Artificial Intelligence and Statistics (AISTAT), Apr 2012, La Palma, Iles Canaries, Spain. pp.592-600
Communication dans un congrès
hal-02286440
v1
|
|
De l'échantillonnage adaptatif à la résolution de jeuxInformatique Mathématique Une photographie en 2022, 2022
Chapitre d'ouvrage
hal-04152484
v1
|
|
Contributions to the Optimal Solution of Several Bandit ProblemsMachine Learning [stat.ML]. Université de Lille, 2020
HDR
tel-03825097
v1
|
|
What Doubling Tricks Can and Can't Do for Multi-Armed Bandits2018
Pré-publication, Document de travail
hal-01736357
v1
|
|
Analysis of bayesian and frequentist strategies for sequential resource allocationMachine Learning [cs.LG]. Télécom ParisTech, 2014. English. ⟨NNT : 2014ENST0056⟩
Thèse
tel-01413183
v1
|
Chargement...
Chargement...