49 citations · 412 across the 50 of their papers we have counts for
5 papers · 2 filters
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…
Generalisation under gradient descent via deterministic PAC-Bayes
Eugenio Clerico, Tyler Farghly, George Deligiannidis +2
We establish disintegrated PAC-Bayesian generalisation bounds for models trained with gradient descent methods or continuous gradient flows. Contrary to standard practice in the PA…
Measuring dissimilarity with diffeomorphism invariance
Théophile Cantelobre, Carlo Ciliberto, Benjamin Guedj +1
Measures of similarity (or dissimilarity) are a key ingredient to many machine learning algorithms. We introduce DID, a pairwise dissimilarity measure applicable to a wide range of…
Change of measure through the Legendre transform
Antoine Picard-Weibel, Benjamin Guedj
PAC-Bayes generalisation bounds are derived via change-of-measure inequalities that transfer concentration properties from a reference measure to all posterior measures. The specif…
Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
Reuben Adams, John Shawe-Taylor, Benjamin Guedj
Current PAC-Bayes generalisation bounds are restricted to scalar metrics of performance, such as the loss or error rate. However, one ideally wants more information-rich certificat…