User-friendly introduction to PAC-Bayes bounds
P Alquier - Foundations and Trends® in Machine Learning, 2024 - nowpublishers.com
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 …
some weights, that is, to some probability distribution. Randomized predictors are obtained …
U-Sleep: resilient high-frequency sleep staging
Sleep disorders affect a large portion of the global population and are strong predictors of
morbidity and all-cause mortality. Sleep staging segments a period of sleep into a sequence …
morbidity and all-cause mortality. Sleep staging segments a period of sleep into a sequence …
Tighter risk certificates for neural networks
This paper presents an empirical study regarding training probabilistic neural networks
using training objectives derived from PAC-Bayes bounds. In the context of probabilistic …
using training objectives derived from PAC-Bayes bounds. In the context of probabilistic …
Learning under model misspecification: Applications to variational and ensemble methods
A Masegosa - Advances in Neural Information Processing …, 2020 - proceedings.neurips.cc
Virtually any model we use in machine learning to make predictions does not perfectly
represent reality. So, most of the learning happens under model misspecification. In this …
represent reality. So, most of the learning happens under model misspecification. In this …
PAC-Bayes analysis beyond the usual bounds
O Rivasplata, I Kuzborskij… - Advances in …, 2020 - proceedings.neurips.cc
We focus on a stochastic learning model where the learner observes a finite set of training
examples and the output of the learning process is a data-dependent distribution over a …
examples and the output of the learning process is a data-dependent distribution over a …
MMD-FUSE: Learning and combining kernels for two-sample testing without data splitting
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 …
Maximum Mean Discrepancy (MMD), byadapting over the set of kernels used in defining it …
Diversity and generalization in neural network ensembles
Ensembles are widely used in machine learning and, usually, provide state-of-the-art
performance in many prediction tasks. From the very beginning, the diversity of an ensemble …
performance in many prediction tasks. From the very beginning, the diversity of an ensemble …
Non-vacuous generalisation bounds for shallow neural networks
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 …
those with $ L_2 $-normalised data and either a sigmoid-shaped Gaussian error function …
Joint training of deep ensembles fails due to learner collusion
Ensembles of machine learning models have been well established as a powerful method of
improving performance over a single model. Traditionally, ensembling algorithms train their …
improving performance over a single model. Traditionally, ensembling algorithms train their …
How tight can PAC-Bayes be in the small data regime?
In this paper, we investigate the question: _Given a small number of datapoints, for example
$ N= 30$, how tight can PAC-Bayes and test set bounds be made? _ For such small …
$ N= 30$, how tight can PAC-Bayes and test set bounds be made? _ For such small …