7 papers · 1 filter
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…
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…
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…
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…
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…
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…