Follow
Etienne Boursier
Etienne Boursier
INRIA Saclay
Verified email at inria.fr - Homepage
Title
Cited by
Cited by
Year
SIC-MMAB: synchronisation involves communication in multiplayer multi-armed bandits
E Boursier, V Perchet
Advances in Neural Information Processing Systems, 12071-12080, 2019
1142019
A practical algorithm for multiplayer bandits when arm means vary among players
E Boursier, E Kaufmann, A Mehrabian, V Perchet
23rd International Conference on Artificial Intelligence and Statistics, 2019
81*2019
Gradient flow dynamics of shallow relu networks for square loss and orthogonal inputs
E Boursier, L Pillaud-Vivien, N Flammarion
Advances in Neural Information Processing Systems 35, 20105-20118, 2022
652022
Statistical efficiency of thompson sampling for combinatorial semi-bandits
P Perrault, E Boursier, M Valko, V Perchet
Advances in Neural Information Processing Systems 33, 5429-5440, 2020
472020
Decentralized Learning in Online Queuing Systems
F Sentenac, E Boursier, V Perchet
Advances in Neural Information Processing Systems 34, 18501-18512, 2021
282021
Selfish robustness and equilibria in multi-player bandits
E Boursier, V Perchet
Conference on Learning Theory, 530-581, 2020
262020
Plato: approximate analytics over compressed time series with tight deterministic error guarantees
C Lin, E Boursier, Y Papakonstantinou
Proceedings of the VLDB Endowment 13 (7), 1105-1118, 2020
24*2020
Penalising the biases in norm regularisation enforces sparsity
E Boursier, N Flammarion
Advances in Neural Information Processing Systems 36, 57795-57824, 2023
152023
Trace norm regularization for multi-task learning with scarce data
E Boursier, M Konobeev, N Flammarion
Conference on Learning Theory, 1303-1327, 2022
132022
Utility/Privacy Trade-off through the lens of Optimal Transport
E Boursier, V Perchet
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2019
11*2019
A Survey on Multi-player Bandits
E Boursier, V Perchet
Journal of Machine Learning Research 25 (137), 1-45, 2024
102024
Early alignment in two-layer networks training is a two-edged sword
E Boursier, N Flammarion
arXiv preprint arXiv:2401.10791, 2024
82024
Efficient approximate query answering over sensor data with deterministic error guarantees
J Brito, K Demirkaya, B Etienne, Y Katsis, C Lin, Y Papakonstantinou
arXiv preprint arXiv:1707.01414, 2017
82017
First-order ANIL provably learns representations despite overparametrisation
OK Yüksel, E Boursier, N Flammarion
The Twelfth International Conference on Learning Representations, 2024
5*2024
Incentivized Learning in Principal-Agent Bandit Games
A Scheid, D Tiapkin, E Boursier, A Capitaine, EME Mhamdi, É Moulines, ...
arXiv preprint arXiv:2403.03811, 2024
42024
Social Learning in Non-Stationary Environments
E Boursier, V Perchet, M Scarsini
International Conference on Algorithmic Learning Theory, 128-129, 2022
4*2022
Making the most of your day: online learning for optimal allocation of time
E Boursier, T Garrec, V Perchet, M Scarsini
Advances in Neural Information Processing Systems 34, 11208-11219, 2021
32021
Optimal Design for Reward Modeling in RLHF
A Scheid, E Boursier, A Durmus, MI Jordan, P Ménard, E Moulines, ...
arXiv preprint arXiv:2410.17055, 2024
12024
Constant or Logarithmic Regret in Asynchronous Multiplayer Bandits with Limited Communication
H Richard, E Boursier, V Perchet
International Conference on Artificial Intelligence and Statistics, 388-396, 2024
1*2024
Simplicity bias and optimization threshold in two-layer ReLU networks
E Boursier, N Flammarion
arXiv preprint arXiv:2410.02348, 2024
2024
The system can't perform the operation now. Try again later.
Articles 1–20