AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Near-Optimal Private Linear Regression via Iterative Hessian Mixing

Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C. Wilson

ICML 2026 · Federated learning and privacy › Differential privacy · approach: Local-DP and private estimation · 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 Iterative Hessian Mixing instead of AdaSSP and LinMix for DP-OLSIHM (T=3, k=6*max{d,log(4T/rho)}, C=C_Y) · 33 UCI linear regression datasets, eps in [0.1,10]normalized excess empirical riskImproved
reduce IHM iterations from T=3 to T=2 on datasets with L(theta*) close to ||Y||^2 (ablation)IHM · Solar, Pendulum, Fertility, Forest, Kin40k, TamiElectric, 3droad, Pumadyn32nm; eps <= 1excess empirical riskImproved
increase IHM iterations and sketch size (T=6, k=12*max{d,log(4T/rho)} vs T=3) (ablation)IHM · Synthetic data with lambda_min(X^TX) about n/d, high epsexcess empirical riskImproved
omit the -eta^2 theta_t term from the noisy gradient (ablation)IHM · empirical evaluationexcess empirical riskImproved
apply sketch only to X (Hessian mixing) rather than to concatenated (X,Y)IHM vs LinMix · DP-OLS, well-conditioned Xnoise level / excess riskImproved
compare IHM with DP-GD baseline (T=3, same clipping, lr 0.25)IHM · UCI datasets, Figures 8-9excess empirical riskImproved
IHM under frequent clipping (violating theorem assumptions)IHM · Synthetic low-rank covariates, more than 40% of iterations clippedexcess empirical riskImproved
use LinMix instead of AdaSSPLinMix · UCI datasetsexcess empirical riskMixed

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