Прати
Paul Viallard
Paul Viallard
Researcher, LACODAM Team, INRIA Rennes, IRISA
Верификована је имејл адреса на inria.fr - Почетна страница
Наслов
Навело
Навело
Година
A PAC-Bayes Analysis of Adversarial Robustness
P Viallard, G Vidot, A Habrard, E Morvant
Advances in Neural Information Processing Systems 34, 2021
332021
A general framework for the practical disintegration of PAC-Bayesian bounds
P Viallard, P Germain, A Habrard, E Morvant
Machine Learning 113 (2), 519-604, 2024
28*2024
Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
V Zantedeschi, P Viallard, E Morvant, R Emonet, A Habrard, P Germain, ...
Advances in Neural Information Processing Systems 34, 455-467, 2021
182021
Learning via Wasserstein-based high probability generalisation bounds
P Viallard, M Haddouche, U Simsekli, B Guedj
Advances in Neural Information Processing Systems 36, 2024
152024
Self-bounding majority vote learning algorithms by the direct minimization of a tight pac-bayesian c-bound
P Viallard, P Germain, A Habrard, E Morvant
Machine Learning and Knowledge Discovery in Databases. Research Track …, 2021
102021
Tighter Generalisation Bounds via Interpolation
P Viallard, M Haddouche, U Şimşekli, B Guedj
arXiv preprint arXiv:2402.05101, 2024
42024
Interpreting neural networks as majority votes through the PAC-Bayesian theory
P Viallard, R Emonet, P Germain, A Habrard, E Morvant
Workshop on Machine Learning with guarantees@ NeurIPS 2019, 2019
42019
A PAC-Bayesian Link Between Generalisation and Flat Minima
M Haddouche, P Viallard, U Simsekli, B Guedj
arXiv preprint arXiv:2402.08508, 2024
32024
From Mutual Information to Expected Dynamics: New Generalization Bounds for Heavy-Tailed SGD
B Dupuis, P Viallard
NeurIPS 2023 Workshop Heavy Tails in Machine Learning, 2023
32023
Leveraging PAC-Bayes Theory and Gibbs Distributions for Generalization Bounds with Complexity Measures
P Viallard, R Emonet, A Habrard, E Morvant, V Zantedeschi
International Conference on Artificial Intelligence and Statistics, 3007-3015, 2024
22024
Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets
B Dupuis, P Viallard, G Deligiannidis, U Simsekli
arXiv preprint arXiv:2404.17442, 2024
12024
A Theoretically Grounded Extension of Universal Attacks from the Attacker's Viewpoint
J Frecon, P Viallard, E Morvant, G Gasso, A Habrard, S Canu
1*
PAC-Bayesian Bounds and Beyond: Self-Bounding Algorithms and New Perspectives on Generalization in Machine Learning
P Viallard
Université Jean Monnet-Saint-Etienne, 2022
2022
Систем тренутно не може да изврши ову радњу. Пробајте поново касније.
Чланци 1–13