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 …

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

We present a unified framework for deriving PAC-Bayesian generalization bounds. Unlike
most previous literature on this topic, our bounds are anytime-valid (ie, time-uniform) …

This paper presents an empirical study regarding training probabilistic neural networks
using training objectives derived from PAC-Bayes bounds. In the context of probabilistic …

Adversarial training has been shown to be one of the most effective approaches to improve
the robustness of deep neural networks. It is formalized as a min-max optimization over …

All famous machine learning algorithms that comprise both supervised and semi-supervised
learning work well only under a common assumption: the training and test data follow the …

Uncertainty estimation is a key factor that makes deep learning reliable in practical
applications. Recently proposed evidential neural networks explicitly account for different …

Sharing information between multiple tasks enables algorithms to achieve good
generalization performance even from small amounts of training data. However, in a realistic …

We exhibit a strong link between frequentist PAC-Bayesian bounds and the Bayesian
marginal likelihood. That is, for the negative log-likelihood loss function, we show that the …