The key distinguishing property of a Bayesian approach is marginalization, rather than using
a single setting of weights. Bayesian marginalization can particularly improve the accuracy …

Bayesian inference is a powerful tool for combining information in complex settings, a task of
increasing importance in modern applications. However, Bayesian inference with a flawed …

The last decade witnessed a growing interest in Bayesian learning. Yet, the technicality of
the topic and the multitude of ingredients involved therein, besides the complexity of turning …

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 draft textbook is extracted from lecture notes from a class that I have taught
(unfortunately online, but this gave me an opportunity to write more detailed notes) during …

We consider the problem of estimating the mean of a sequence of random elements $ f
(\theta, X_1) $$,\ldots, $$ f (\theta, X_n) $ where $ f $ is a fixed scalar function …

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 …

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 …

Deep learning has achieved remarkable success in many machine learning tasks such as
image classification, speech recognition, and game playing. However, these breakthroughs …

Abstract Since their inception, Variational Autoencoders (VAEs) have become central in
machine learning. Despite their widespread use, numerous questions regarding their …