1 code implementation • 30 Sep 2023 • Quentin Bertrand, Avishek Joey Bose, Alexandre Duplessis, Marco Jiralerspong, Gauthier Gidel
In this paper, we develop a framework to rigorously study the impact of training generative models on mixed datasets -- from classical training on real data to self-consuming generative models trained on purely synthetic data.
no code implementations • 12 Jul 2023 • Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis
In this work, we introduce and analyse a novel aggregation framework that allows for formalizing and tackling computational heterogeneity in federated optimization, in terms of both heterogeneous data and local updates.
no code implementations • 27 May 2022 • Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis, David Naccache
To date, the most popular federated learning algorithms use coordinate-wise averaging of the model parameters.
no code implementations • 22 May 2022 • Adnan Ben Mansour, Gaia Carenini, Alexandre Duplessis, David Naccache
The resulting model is then redistributed to clients for further training.