AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Unified Privacy Guarantees for Decentralized Learning via Matrix Factorization

Aurélien Bellet, Edwige Cyffers, Davide Frey, Romaric Gaudel, Dimitri Lerévérend, Francois Taiani

ICLR 2026 · Federated learning and privacy › Differential privacy · approach: Private training with public data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use optimized local noise correlation (MAFALDA-SGD) instead of uncorrelated noise (DP-D-SGD)decentralized SGD under LDP · Housing, Facebook Ego graphtest loss: 31% average improvement in test loss; 2-fold reduction in epsilon at test loss 0.75Improved
use optimized correlation instead of AntiPGD correlation in decentralized settingdecentralized SGD under LDP · Housing, Facebook Ego graphtest loss: AntiPGD test loss always greater than 6Improved
use matrix factorization PNDP accounting instead of prior accountingDP-D-SGD · Erdos-Renyi, Facebook Ego, PeerTube, Florentine graphsprivacy loss (Renyi divergence): up to an order of magnitude at distance <=2; at least two orders at distance >=3Improved
use MAFALDA-SGD correlated noise instead of private baselinesdecentralized SGD under LDP · FEMNIST, Facebook Ego graphtest accuracyImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy