Aggregated predictors are obtained by making a set of basic predictors vote according to
some weights, that is, to some probability distribution. Randomized predictors are obtained …

A fundamental question in theoretical machine learning is generalization. Over the past
decades, the PAC-Bayesian approach has been established as a flexible framework to …

While PAC-Bayes is now an established learning framework for light-tailed losses (\emph
{eg}, subgaussian or subexponential), its extension to the case of heavy-tailed losses …

We propose novel statistics which maximise the power of a two-sample test based on the
Maximum Mean Discrepancy (MMD), byadapting over the set of kernels used in defining it …

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-Bayesian …

We focus on a specific class of shallow neural networks with a single hidden layer, namely
those with $ L_2 $-normalised data and either a sigmoid-shaped Gaussian error function …

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 …

We extend PAC-Bayesian theory to generative models and develop generalization bounds
for models based on the Wasserstein distance and the total variation distance. Our first result …

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 state …

In this paper, we establish novel data-dependent upper bounds on the generalization error
through the lens of a “variable-size compressibility” framework that we introduce newly here …