We study the generalisation properties of majority voting on finite ensembles of classifiers,
proving margin-based generalisation bounds via the PAC-Bayes theory. These provide state …

We present a new second-order oracle bound for the expected risk of a weighted majority
vote. The bound is based on a novel parametric form of the Chebyshev-Cantelli inequality …

We investigate a stochastic counterpart of majority votes over finite ensembles of classifiers,
and study its generalization properties. While our approach holds for arbitrary distributions …

Most human beings don't manage to achieve fame. Roy did it for two different reasons. In
2005, he received the Nobel Prize in Physics, a scientific recognition that is only awarded to …

The PAC-Bayesian framework has significantly advanced our understanding of statistical
learning, particularly in majority voting methods. However, its application to multi-view …

Generalisation in machine learning refers to the ability of a predictor learned on some
dataset to perform accurately on new, unseen data. Without generalisation, we might be …

Deep Learning for Optimization in Operations Research Enhancing Resource Allocation,
Computational Efficiency, and Generalizatio Page 1 Deep Learning for Optimization in …

The weighted majority vote is part of the winning strategies in many machine learning
competitions. It is an integral part of random forests and boosting and is also used to …

Learning with partially labeled data, known as semi-supervised learning, deals with
problems where few training examples are labeled while available unlabeled data are …