no code implementations • 5 Jun 2023 • Batiste Le Bars, Aurélien Bellet, Marc Tommasi, Kevin Scaman, Giovanni Neglia
On the contrary, we show, for convex, strongly convex and non-convex functions, that D-SGD can always recover generalization bounds analogous to those of classical SGD, suggesting that the choice of graph does not matter.
1 code implementation • 13 Feb 2023 • Pierre Humbert, Batiste Le Bars, Aurélien Bellet, Sylvain Arlot
In this paper, we introduce a conformal prediction method to construct prediction sets in a oneshot federated learning setting.
no code implementations • 9 Apr 2022 • Batiste Le Bars, Aurélien Bellet, Marc Tommasi, Erick Lavoie, Anne-Marie Kermarrec
One of the key challenges in decentralized and federated learning is to design algorithms that efficiently deal with highly heterogeneous data distributions across agents.
1 code implementation • 30 Jun 2020 • Pierre Humbert, Batiste Le Bars, Ludovic Minvielle, Nicolas Vayatis
In this paper, we introduce a robust nonparametric density estimator combining the popular Kernel Density Estimation method and the Median-of-Means principle (MoM-KDE).
no code implementations • ICML 2020 • Batiste Le Bars, Pierre Humbert, Argyris Kalogeratos, Nicolas Vayatis
This work focuses on the estimation of multiple change-points in a time-varying Ising model that evolves piece-wise constantly.
no code implementations • 12 Feb 2019 • Batiste Le Bars, Argyris Kalogeratos
In this paper we consider the task of detecting abnormal communication volume occurring at node-level in communication networks.