5 papers
Optimization Trade-offs in Asynchronous Federated Learning: A Stochastic Networks Approach
Abdelkrim Alahyane, Céline Comte, Matthieu Jonckheere
Synchronous federated learning scales poorly due to the straggler effect. Asynchronous algorithms increase the update throughput by processing updates upon arrival, but they introd…
means with learned metrics
Pablo Groisman, Matthieu Jonckheere, Jordan Serres +1
We study the Fréchet means of a metric measure space when both the measure and the distance are unknown and have to be estimated. We prove a general result that states that the…
Optimizing Asynchronous Federated Learning: A Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency
Abdelkrim Alahyane, Céline Comte, Matthieu Jonckheere +1
Synchronous federated learning (FL) scales poorly with the number of clients due to the straggler effect. Algorithms like FedAsync and GeneralizedFedAsync address this limitation b…
Score-Aware Policy-Gradient and Performance Guarantees using Local Lyapunov Stability
Céline Comte, Matthieu Jonckheere, Jaron Sanders +1
In this paper, we introduce a policy-gradient method for model-based reinforcement learning (RL) that exploits a type of stationary distributions commonly obtained from Markov deci…
Stochastic bounds for two-layer loss systems
Matthieu Jonckheere, Lasse Leskela
This paper studies multiclass loss systems with two layers of servers, where each server at the first layer is dedicated to a certain customer class, while the servers at the secon…