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 …

We advocate an optimization-centric view of Bayesian inference. Our inspiration is the
representation of Bayes' rule as infinite-dimensional optimization (Csisz´ r, 1975; Donsker …

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) …

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate
learning of novel future tasks. Under the assumption that future tasks are 'related'to previous …

Various approaches have been developed to upper bound the generalization error of a
supervised learning algorithm. However, existing bounds are often loose and lack of …

Deep transfer learning has become increasingly prevalent in various fields such as industry
and medical science in recent years. To ensure the successful implementation of target …

The dominant term in PAC-Bayes bounds is often the Kullback-Leibler divergence between
the posterior and prior. For so-called linear PAC-Bayes risk bounds based on the empirical …

Abstract The Probably Approximately Correct (PAC) Bayes framework (McAllester, 1999)
can incorporate knowledge about the learning algorithm and (data) distribution through the …

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 …