Publications

2023

• P. Viallard, M.Haddouche, U. Simsekli, B.Guedj, Learning via Wasserstein-Based High Probability Generalisation Bounds, Neurips 2023
• M. Haddouche, B. Guedj, PAC-Bayes Generalisation Bounds for Heavy-Tailed Losses through Supermartingales, Transactions on Machine Learning Research.

2022

• M. Haddouche, B. Guedj, Online PAC-Bayes Learning, Neurips 2022

2021

• M. Haddouche, B. Guedj, O. Rivasplata and J. Shawe-Taylor. PAC-Bayes Unleashed: Generalisation Bounds with Unbounded Losses. Published at MDPI,Entropy, 2021.

Preprints

• M. Haddouche, P. Viallard, U. Simsekli, B.Guedj, A PAC-Bayesian Link Between Generalisation and Flat Minima
• P. Viallard, M. Haddouche, U. Simsekli, B. Guedj, Tighter Generalisation Bounds via Interpolation
• P.Jobic, M.Haddouche, B. Guedj, Federated Learning with Nonvacuous Generalisation Bounds
• M. Haddouche, B. Guedj, Wasserstein PAC-Bayes Learning: Exploiting Optimisation Guarantees to Explain Generalisation.
• M. Haddouche, O. Wintenberger, B. Guedj Optimistically Tempered Online Learning.
• M. Haddouche, B. Guedj, O. Rivasplata and J. Shawe-Taylor. Upper and Lower Bounds on the Performance of Kernel PCA.