Maxime Haddouche

According to our database, Maxime Haddouche authored at least 15 papers between 2020 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Logarithmic Smoothing for Adaptive PAC-Bayesian Off-Policy Learning.

Maxime Haddouche, Otmane Sakhi

CoRR, June, 2025

Algorithm- and Data-Dependent Generalization Bounds for Score-Based Generative Models.

Benjamin Dupuis, Dario Shariatian, Maxime Haddouche, Alain Durmus, Umut Simsekli

CoRR, June, 2025

Online Decision-Focused Learning.

Aymeric Capitaine, Maxime Haddouche, Eric Moulines, Michael I. Jordan, Etienne Boursier, Alain Durmus

CoRR, May, 2025

Understanding the Generalization Error of Markov algorithms through Poissonization.

Benjamin Dupuis, Maxime Haddouche, George Deligiannidis, Umut Simsekli

CoRR, February, 2025

A PAC-Bayesian Link Between Generalisation and Flat Minima.

Maxime Haddouche, Paul Viallard, Umut Simsekli, Benjamin Guedj

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

2024

Tighter Generalisation Bounds via Interpolation.

Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj

CoRR, 2024

2023

PAC-Bayes Generalisation Bounds for Heavy-Tailed Losses through Supermartingales.

Maxime Haddouche, Benjamin Guedj

Trans. Mach. Learn. Res., 2023

Federated Learning with Nonvacuous Generalisation Bounds.

Pierre Jobic, Maxime Haddouche, Benjamin Guedj

CoRR, 2023

Wasserstein PAC-Bayes Learning: A Bridge Between Generalisation and Optimisation.

Maxime Haddouche, Benjamin Guedj

CoRR, 2023

Optimistic Dynamic Regret Bounds.

Maxime Haddouche, Benjamin Guedj, Olivier Wintenberger

CoRR, 2023

Learning via Wasserstein-Based High Probability Generalisation Bounds.

Paul Viallard, Maxime Haddouche, Umut Simsekli, Benjamin Guedj

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

PAC-Bayes with Unbounded Losses through Supermartingales.

Maxime Haddouche, Benjamin Guedj

CoRR, 2022

Online PAC-Bayes Learning.

Maxime Haddouche, Benjamin Guedj

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

PAC-Bayes Unleashed: Generalisation Bounds with Unbounded Losses.

Maxime Haddouche, Benjamin Guedj, Omar Rivasplata, John Shawe-Taylor

Entropy, 2021

2020

Upper and Lower Bounds on the Performance of Kernel PCA.

Maxime Haddouche, Benjamin Guedj, Omar Rivasplata, John Shawe-Taylor

CoRR, 2020