Suivre
Maxime Haddouche
Maxime Haddouche
Adresse e-mail validée de inria.fr
Titre
Citée par
Citée par
Année
PAC-Bayes unleashed: Generalisation bounds with unbounded losses
M Haddouche, B Guedj, O Rivasplata, J Shawe-Taylor
Entropy 23 (10), 1330, 2021
512021
PAC-Bayes Generalisation Bounds for Heavy-Tailed Losses through Supermartingales
M Haddouche, B Guedj
Transactions on Machine Learning Research, 2022
282022
Online PAC-Bayes Learning
M Haddouche, B Guedj
Advances in Neural Information Processing Systems 35, 2022
212022
Learning via Wasserstein-based high probability generalisation bounds
P Viallard, M Haddouche, U Simsekli, B Guedj
Advances in Neural Information Processing Systems 36, 2024
72024
Wasserstein PAC-Bayes Learning: Exploiting Optimisation Guarantees to Explain Generalisation
M Haddouche, B Guedj
arXiv preprint arXiv:2304.07048, 2023
6*2023
Upper and lower bounds on the performance of kernel PCA
M Haddouche, B Guedj, J Shawe-Taylor
arXiv preprint arXiv:2012.10369, 2020
52020
Tighter Generalisation Bounds via Interpolation
P Viallard, M Haddouche, U Şimşekli, B Guedj
arXiv preprint arXiv:2402.05101, 2024
22024
Federated Learning with Nonvacuous Generalisation Bounds
P Jobic, M Haddouche, B Guedj
arXiv preprint arXiv:2310.11203, 2023
12023
Optimistic dynamic regret bounds
M Haddouche, B Guedj, O Wintenberger
arXiv preprint arXiv:2301.07530, 2023
12023
A PAC-Bayesian Link Between Generalisation and Flat Minima
M Haddouche, P Viallard, U Simsekli, B Guedj
arXiv preprint arXiv:2402.08508, 2024
2024
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–10