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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace Laplace noise (epsilon-certifiability) with Gaussian noise (GPAR) in one-step Newton unlearning (ablation) | Newton unlearning · Logistic regression simulation, m=1,5,10 | slope 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=1255 | GED | Improved |
| increase number of removed points m (ablation) | Newton unlearning · Logistic regression simulation eps=0.75 | GED: Gaussian slope 1.37, 1.42, 1.44 vs m | Hurt |
| Laplace-noise one-step Newton as dimension p grows (ablation) | Newton unlearning with Laplace noise · Logistic regression simulation | GED: slopes 0.03, -0.03, -0.01 | No clear effect |
Closest papers by meaning
- Hessian-Free Online Certified Unlearning (ICLR 2025 · similarity 0.88)
- Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions (NeurIPS 2025 · similarity 0.88)
- Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning (NeurIPS 2024 · similarity 0.87)
- Certified Machine Unlearning via Noisy Stochastic Gradient Descent (NeurIPS 2024 · similarity 0.87)
- The Utility and Complexity of In- and Out-of-Distribution Machine Unlearning (ICLR 2025 · similarity 0.87)
- Certified Unlearning for Neural Networks (ICML 2025 · similarity 0.87)
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.
