10 citations · 22 across the 11 of their papers we have counts for
7 papers · 1 filter
Generalization Bounds for Markov Algorithms through Entropy Flow Computations
Benjamin Dupuis, Maxime Haddouche, George Deligiannidis +1
Many learning algorithms can be represented as Markov processes, and understanding their generalization error is a central topic in learning theory. For specific continuous-time no…
Tighter Generalisation Bounds via Interpolation
Paul Viallard, Maxime Haddouche, Umut Şimşekli +1
This paper contains a recipe for deriving new PAC-Bayes generalisation bounds based on the -divergence, and, in addition, presents PAC-Bayes generalisation bounds where we…
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…
Learning via Wasserstein-Based High Probability Generalisation Bounds
Paul Viallard, Maxime Haddouche, Umut Şimşekli +1
Minimising upper bounds on the population risk or the generalisation gap has been widely used in structural risk minimisation (SRM) -- this is in particular at the core of PAC-Baye…
Wasserstein PAC-Bayes Learning: Exploiting Optimisation Guarantees to Explain Generalisation
Maxime Haddouche, Benjamin Guedj
PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation boun…
PAC-Bayes Generalisation Bounds for Heavy-Tailed Losses through Supermartingales
Maxime Haddouche, Benjamin Guedj
While PAC-Bayes is now an established learning framework for light-tailed losses (\emph{e.g.}, subgaussian or subexponential), its extension to the case of heavy-tailed losses rema…
PAC-Bayes unleashed: generalisation bounds with unbounded losses
Maxime Haddouche, Benjamin Guedj, Omar Rivasplata +1
We present new PAC-Bayesian generalisation bounds for learning problems with unbounded loss functions. This extends the relevance and applicability of the PAC-Bayes learning framew…