REDEEM Project
News
Publications
Job offer
People
English
English
Français
INRIA-ARGO
Certificates in P and Subquadratic-Time Computation of Radius, Diameter, and All Eccentricities in Graphs
In the context of fine-grained complexity, we investigate the notion of certificate enabling faster polynomialtime algorithms. We …
Feodor Dragan
,
Guillaume Ducoffe
,
Michel Habib
,
Laurent Viennot
Cite
DOI
URL
In-Depth Analysis of Low-rank Matrix Factorisation in a Federated Setting
We analyze a distributed algorithm to compute a low-rank matrix factorization on $N$ clients, each holding a local dataset $ …
Constantin Philippenko
,
Kevin Scaman
,
Laurent Massoulié
Cite
DOI
URL
Improved Stability and Generalization Guarantees of the Decentralized SGD Algorithm
This paper presents a new generalization error analysis for Decentralized Stochastic Gradient Descent (D-SGD) based on algorithmic …
Batiste Le Bars
,
Aurélien Bellet
,
Marc Tommasi
,
Kevin Scaman
,
Giovanni Neglia
Cite
Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles
In this paper, our aim is to analyse the generalization capabilities of first-order methods for statistical learning in multiple, …
Kevin Scaman
,
Mathieu Even
,
Batiste Le Bars
,
Laurent Massoulié
Cite
URL
SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given …
Yann Fraboni
,
Martin Van Waerebeke
,
Kevin Scaman
,
Richard Vidal
,
Laetitia Kameni
,
Marco Lorenzi
Cite
URL
Cite
×