AI Paper Atlas

Research map / Federated learning and privacy / Differential privacy

Gaussian certified unlearning in high dimensions: A hypothesis testing approach

Aaradhya Pandey, Arnab Auddy, Haolin Zou, Arian Maleki, Sanjeev Kulkarni

ICLR 2026 · Federated learning and privacy › Differential privacy · approach: Private online and user-level learning · 3 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
replace Laplace noise (epsilon-certifiability) with Gaussian noise (GPAR) in one-step Newton unlearning (ablation)Newton unlearning · Logistic regression simulation, m=1,5,10slope of log GED vs log p: 0.03 -> -0.47 (m=1)Improved
increase epsilon for Gaussian-perturbed unlearning (ablation)Newton unlearning with Gaussian noise · Logistic regression simulation n=p=1255GEDImproved
increase number of removed points m (ablation)Newton unlearning · Logistic regression simulation eps=0.75GED: Gaussian slope 1.37, 1.42, 1.44 vs mHurt
Laplace-noise one-step Newton as dimension p grows (ablation)Newton unlearning with Laplace noise · Logistic regression simulationGED: slopes 0.03, -0.03, -0.01No clear effect

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