Прати
Rémy Degenne
Rémy Degenne
Inria Lille
Верификована је имејл адреса на inria.fr - Почетна страница
Наслов
Навело
Навело
Година
Non-asymptotic pure exploration by solving games
R Degenne, WM Koolen, P Ménard
Advances in Neural Information Processing Systems 32, 2019
1152019
Gamification of pure exploration for linear bandits
R Degenne, P Ménard, X Shang, M Valko
International Conference on Machine Learning, 2432-2442, 2020
1042020
Pure exploration with multiple correct answers
R Degenne, WM Koolen
Advances in Neural Information Processing Systems 32, 2019
932019
Anytime optimal algorithms in stochastic multi-armed bandits
R Degenne, V Perchet
International Conference on Machine Learning, 1587-1595, 2016
712016
Combinatorial semi-bandit with known covariance
R Degenne, V Perchet
Advances in Neural Information Processing Systems 29, 2016
642016
Top two algorithms revisited
M Jourdan, R Degenne, D Baudry, R de Heide, E Kaufmann
Advances in Neural Information Processing Systems 35, 26791-26803, 2022
542022
Structure adaptive algorithms for stochastic bandits
R Degenne, H Shao, W Koolen
International Conference on Machine Learning, 2443-2452, 2020
452020
Bridging the gap between regret minimization and best arm identification, with application to a/b tests
R Degenne, T Nedelec, C Calauzènes, V Perchet
The 22nd International Conference on Artificial Intelligence and Statistics …, 2019
262019
On the existence of a complexity in fixed budget bandit identification
R Degenne
The Thirty Sixth Annual Conference on Learning Theory, 1131-1154, 2023
242023
Dealing with unknown variances in best-arm identification
M Jourdan, D Rémy, K Emilie
International Conference on Algorithmic Learning Theory, 776-849, 2023
202023
Non-asymptotic analysis of a ucb-based top two algorithm
M Jourdan, R Degenne
Advances in Neural Information Processing Systems 36, 68980-69020, 2023
162023
An -Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
M Jourdan, R Degenne, E Kaufmann
Advances in Neural Information Processing Systems 36, 16578-16649, 2023
152023
On elimination strategies for bandit fixed-confidence identification
A Tirinzoni, R Degenne
Advances in Neural Information Processing Systems 35, 18586-18598, 2022
142022
Dealing with misspecification in fixed-confidence linear top-m identification
C Réda, A Tirinzoni, R Degenne
Advances in Neural Information Processing Systems 34, 25489-25501, 2021
142021
Bandits with side observations: Bounded vs. logarithmic regret
R Degenne, E Garcelon, V Perchet
arXiv preprint arXiv:1807.03558, 2018
122018
Choosing answers in epsilon-best-answer identification for linear bandits
M Jourdan, R Degenne
International Conference on Machine Learning, 10384-10430, 2022
82022
Impact of structure on the design and analysis of bandit algorithms
R Degenne
Université Paris Cité, 2019
82019
Accelerated gradient temporal difference learning algorithms
D Meyer, R Degenne, A Omrane, H Shen
2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement …, 2014
82014
Online sign identification: Minimization of the number of errors in thresholding bandits
R Ouhamma, R Degenne, P Gaillard, V Perchet
Advances in Neural Information Processing Systems 34, 18577-18589, 2021
72021
Optimal multi-fidelity best-arm identification
R Poiani, R Degenne, E Kaufmann, AM Metelli, M Restelli
arXiv preprint arXiv:2406.03033, 2024
42024
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–20