Microsoft (France)

output

20122024

most citedSAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives

927 citations

researchers with a paper here

F. Bach3 · h 108
Anthony Leverrier2 · h 37
Hadrien Hendrikx2 · h 13
L. Massouli'e2 · h 9
L. Massoulié2 · h 52
V. Londe2 · h 5
Aaron Defazio1 · h 23
A. Auger1 · h 40
A. Bellet1 · h 32
A. Chotard1 · h 5
Charlie Hewitt1 · h 4
Darren Cosker1 · h 3

collaborating institutions

Institut national de recherche en sciences et technologies du numériqueFR10 papers
École Normale Supérieure - PSLFR3 papers
Centre Inria de SaclayFR2 papers
Centre National de la Recherche ScientifiqueFR2 papers
Laboratoire de Recherche en InformatiqueFR2 papers
COSMIQ: Cryptologie symétrique, cryptologie fondée sur les codes et information quantiqueFR1 paper
Data61AU1 paper
Département de mathématiques et applicationsFR1 paper
Département d'InformatiqueFR1 paper
DYOGENE: Dynamics of Geometric NetworksFR1 paper
Institut de Mathématiques de BordeauxFR1 paper
MAGNET: Machine Learning in Information NetworksFR1 paper

Showing cs.CRShow all

1 paper · 1 filter

cs.CR2022★ 1 cited

Muffliato: Peer-to-Peer Privacy Amplification for Decentralized Optimization and Averaging

Edwige Cyffers, Mathieu Even, Aurélien Bellet +1

Decentralized optimization is increasingly popular in machine learning for its scalability and efficiency. Intuitively, it should also provide better privacy guarantees, as nodes o…