KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints A Garivier, H Hadiji, P Menard, G Stoltz Journal of Machine Learning Research 23 (179), 1-66, 2022 | 43 | 2022 |
Between stochastic and adversarial online convex optimization: Improved regret bounds via smoothness S Sachs, H Hadiji, T van Erven, C Guzmán Advances in Neural Information Processing Systems 35, 691-702, 2022 | 16 | 2022 |
Polynomial cost of adaptation for x-armed bandits H Hadiji Advances in Neural Information Processing Systems, 2019, 2019 | 16 | 2019 |
Adaptation to the range in k-armed bandits H Hadiji, G Stoltz Journal of Machine Learning Research 24 (13), 1-33, 2023 | 12 | 2023 |
Scale-free Unconstrained Online Learning for Curved Losses JJ Mayo, H Hadiji, T van Erven Conference on Learning Theory, 2022 | 11 | 2022 |
Distributed online learning for joint regret with communication constraints D Van der Hoeven, H Hadiji, T van Erven International Conference on Algorithmic Learning Theory, 1003-1042, 2022 | 4 | 2022 |
Accelerated rates between stochastic and adversarial online convex optimization S Sachs, H Hadiji, T van Erven, C Guzman arXiv preprint arXiv:2303.03272, 2023 | 3 | 2023 |
Tracking solutions of time-varying variational inequalities H Hadiji, S Sachs, C Guzmán arXiv preprint arXiv:2406.14059, 2024 | 1 | 2024 |
On some adaptivity questions in stochastic multi-armed bandits H Hadiji Université Paris-Saclay, 2020 | 1 | 2020 |
Diversity-Preserving K-Armed Bandits, Revisited H Hadiji, S Gerchinovitz, JM Loubes, G Stoltz arXiv preprint arXiv:2010.01874, 2020 | 1 | 2020 |
Towards characterizing the first-order query complexity of learning (approximate) nash equilibria in zero-sum matrix games H Hadiji, S Sachs, T van Erven, WM Koolen Advances in Neural Information Processing Systems 36, 2024 | | 2024 |
KL-UCB-switch: un nouvel algorithme de bandit asymptotiquement optimal et minimax optimal H Hadiji, A Garivier, P Ménard, G Stoltz | | |