Search Results for author: Batiste Le Bars

Found 6 papers, 2 papers with code

Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm

no code implementations5 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.

Generalization Bounds

One-Shot Federated Conformal Prediction

1 code implementation13 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.

Conformal Prediction Federated Learning

Refined Convergence and Topology Learning for Decentralized SGD with Heterogeneous Data

no code implementations9 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.

Federated Learning

Robust Kernel Density Estimation with Median-of-Means principle

1 code implementation30 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).

Density Estimation

Learning the piece-wise constant graph structure of a varying Ising model

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.

A Probabilistic Framework to Node-level Anomaly Detection in Communication Networks

no code implementations12 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.

Anomaly Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.