activity
20242026
collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Beyond Softmax and Entropy: Convergence Rates of Policy Gradients with f-SoftArgmax Parameterization & Coupled Regularization

Safwan Labbi, Daniil Tiapkin, Paul Mangold +1

Policy gradient methods are known to be highly sensitive to the choice of policy parameterization. In particular, the widely used softmax parameterization can induce ill-conditione…

cs.LG2025

Convergence Guarantees for Federated SARSA with Local Training and Heterogeneous Agents

Paul Mangold, Eloïse Berthier, Eric Moulines

We present a novel theoretical analysis of Federated SARSA (FedSARSA) with linear function approximation and local training. We establish convergence guarantees for FedSARSA in the…

cs.LG2025

On Global Convergence Rates for Federated Softmax Policy Gradient under Heterogeneous Environments

Safwan Labbi, Paul Mangold, Daniil Tiapkin +1

We provide global convergence rates for vanilla and entropy-regularized federated softmax stochastic policy gradient (FedPG) with local training. We show that FedPG converges to a…

cs.LG2025

Online Decision-Focused Learning

Aymeric Capitaine, Maxime Haddouche, Eric Moulines +3

Decision-focused learning (DFL) is an increasingly popular paradigm for training predictive models whose outputs are used in decision-making tasks. Instead of merely optimizing for…

cs.LG2025

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…

cs.LG2024

Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents

Safwan Labbi, Daniil Tiapkin, Lorenzo Mancini +2

In this paper, we present the Federated Upper Confidence Bound Value Iteration algorithm (), a novel extension of the algorithm (Azar et al., 2…