As data generation increasingly takes place on devices without a wired connection, Machine
Learning (ML) related traffic will be ubiquitous in wireless networks. Many studies have …

Abstract The objective of Federated Learning (FL) is to perform statistical inference for data
which are decentralised and stored locally on networked clients. FL raises many constraints …

Most works on federated learning (FL) focus on the most common frequentist formulation of
learning whereby the goal is minimizing the global empirical loss. Frequentist learning …

Artificial intelligence (AI) algorithms based on neural networks have been designed for
decades with the goal of maximising some measure of accuracy. This has led to two …

Distributed learning has become a promising computational parallelism paradigm that
enables a wide scope of intelligent applications from the Internet of Things (IoT) to …

The recent development of scalable Bayesian inference methods has renewed interest in
the adoption of Bayesian learning as an alternative to conventional frequentist learning that …

Résumé Centraliser les données est indésirable dans de nombreux scénarios, notamment
lorsque des informations sensibles sont traitées. Dans de tels cas, la nécessité de méthodes …

The next-generation mobile communication system, eg, 6G communication system, is
envisioned to support unprecedented performance requirements such as exponentially …

This paper studies distributed Bayesian learning in a setting encompassing a central server
and multiple workers by focusing on the problem of mitigating the impact of stragglers. The …