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 …

Federated learning faces huge challenges from model overfitting due to the lack of data and
statistical diversity among clients. To address these challenges, this paper proposes a novel …

Generalised Bayesian learning algorithms are increasingly popular in machine learning,
due to their PAC generalisation properties and flexibility. The present paper aims at …

We study convergence rates of variational posterior distributions for nonparametric and high-
dimensional inference. We formulate general conditions on prior, likelihood and variational …

Sparse deep learning aims to address the challenge of huge storage consumption by deep
neural networks, and to recover the sparse structure of target functions. Although …

In some misspecified settings, the posterior distribution in Bayesian statistics may lead to
inconsistent estimates. To fix this issue, it has been suggested to replace the likelihood by a …

Bayesian models are powerful tools for studying complex data, allowing the analyst to
encode rich hierarchical dependencies and leverage prior information. Most importantly …

Variational inference has become an increasingly attractive fast alternative to Markov chain
Monte Carlo methods for approximate Bayesian inference. However, a major obstacle to 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 …

Variational Bayes (VB) is a scalable alternative to Markov chain Monte Carlo (MCMC) for
Bayesian posterior inference. Though popular, VB comes with few theoretical guarantees …