4 papers
A PAC-Bayesian View of Generalisation for Physics-Informed Machine Learning
Thien V. Nguyen, Amaury Habrard, Benjamin Guedj
Physics-informed machine learning (PIML) integrates mechanistic knowledge, typically in the form of partial differential equations (PDE), into data-driven models. Despite strong em…
Federated Learning with Nonvacuous Generalisation Bounds
Pierre Jobic, Maxime Haddouche, Benjamin Guedj
We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but…
Rapidly Varying Completely Random Measures for Modeling Extremely Sparse Networks
Valentin Kilian, Benjamin Guedj, François Caron
Completely random measures (CRMs) are fundamental to Bayesian nonparametric models, with applications in clustering, feature allocation, and network analysis. A key quantity of int…
A PAC-Bayesian Link Between Generalisation and Flat Minima
Maxime Haddouche, Paul Viallard, Umut Simsekli +1
Modern machine learning usually involves predictors in the overparameterised setting (number of trained parameters greater than dataset size), and their training yields not only go…