Newest papers

Federated Differentially Private Optimization via Low-Rank Preconditioning

Antti Koskela, Tejas Kulkarni, Elias Raninen · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31069 · cited by 0 works (OpenAlex) · open-access PDF

German

Wir betrachten Differential Private (DP) Optimierung in der federierten Einstellung, wo eine DP-Schätzung der Feature-Covariance-Matrix dient als eine Hessische Annäherung für generalisierte lineare Modelle. Bestehende zentrale DP-Methoden für die Covariance-Schätzung haben Kommunikationskosten, die quadratisch in der Datendimension wachsen, während bestehende Basislinien mit linearen Kommunikationskosten nur lokal privat sind und sich verringern, wenn die Anzahl der Kunden zunimmt. Als Heilmittel schlagen wir einen federierten DP-PCA-Framework vor, der lineare Kommunikationskosten erreicht und zentrale DP-Garantien unter sicherer Aggregation bietet. Es besteht aus einem DP-Rang-Auswahlschritt, einer DP-Leistungsmet

Machine translation (Meta M2M100); the English original follows.

Abstract

We consider differentially private (DP) optimization in the federated setting, where a DP estimate of the feature covariance matrix serves as a Hessian approximation for generalized linear models. Existing central DP methods for covariance estimation have communication cost that grows quadratically in the data dimension, while existing baselines with linear communication cost are only locally private and degrade as the number of clients increases. As a remedy, we propose a federated DP-PCA framework that achieves linear communication cost while providing central DP guarantees under secure aggregation. It consists of a DP rank selection step, a DP power method, and a noisy release of the covariance projected onto the selected low-dimensional subspace. We give error bounds for this covariance estimate and for the resulting low-communication preconditioned DP gradient descent. Empirically, our proposed DP optimization method matches a centralized baseline with quadratic communication cost at a fraction of the communication.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Covariance, Hessian matrix, Covariance matrix, Computer science, Mathematical optimization, Estimation of covariance matrices

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange