49 citations · 412 across the 50 of their papers we have counts for
12 papers · 1 filter
Tighter PAC-Bayes Generalisation Bounds by Leveraging Example Difficulty
Felix Biggs, Benjamin Guedj
We introduce a modified version of the excess risk, which can be used to obtain tighter, fast-rate PAC-Bayesian generalisation bounds. This modified excess risk leverages informati…
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…
Opening up echo chambers via optimal content recommendation
Antoine Vendeville, Anastasios Giovanidis, Effrosyni Papanastasiou +1
Online social platforms have become central in the political debate. In this context, the existence of echo chambers is a problem of primary relevance. These clusters of like-minde…
On Margins and Generalisation for Voting Classifiers
Felix Biggs, Valentina Zantedeschi, Benjamin Guedj
We study the generalisation properties of majority voting on finite ensembles of classifiers, proving margin-based generalisation bounds via the PAC-Bayes theory. These provide sta…
Online PAC-Bayes Learning
Maxime Haddouche, Benjamin Guedj
Most PAC-Bayesian bounds hold in the batch learning setting where data is collected at once, prior to inference or prediction. This somewhat departs from many contemporary learning…
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…
Discord in the voter model for complex networks
Antoine Vendeville, Shi Zhou, Benjamin Guedj
Online social networks have become primary means of communication. As they often exhibit undesirable effects such as hostility, polarisation or echo chambers, it is crucial to deve…
On PAC-Bayesian reconstruction guarantees for VAEs
Badr-Eddine Chérief-Abdellatif, Yuyang Shi, Arnaud Doucet +1
Despite its wide use and empirical successes, the theoretical understanding and study of the behaviour and performance of the variational autoencoder (VAE) have only emerged in the…
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…
Non-Vacuous Generalisation Bounds for Shallow Neural Networks
Felix Biggs, Benjamin Guedj
We focus on a specific class of shallow neural networks with a single hidden layer, namely those with -normalised data and either a sigmoid-shaped Gaussian error function ("er…