Research map / Learning theory and algorithms / Prediction and decision losses
Certified Machine Unlearning Under High Dimensional Regime
Haolin Zou, Arnab Auddy, Yongchan Kwon, Kamiar Rahnama Rad, Arian Maleki
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 |
|---|---|---|---|
| use two Newton steps instead of one (ablation) | Newton-step certified unlearning, ridge logistic regression · Ridge logistic regression, m=1 | approximation error scaling in n: n^-0.5 -> n^-1.5 | Improved |
| use two Newton steps instead of one so less noise is needed for certification (ablation) | Certified Newton unlearning plus Laplace noise · Ridge logistic regression, loss difference to exact unlearned model | loss error after noise | Improved |
| compare against Guo et al. 2019 single-step method | two-step Newton · Ridge logistic regression, single deletion (Figure 1) | loss alignment with exact unlearning | Improved |
| apply to sparse real bag-of-words data (IMDB) | Newton unlearning theory · IMDB ridge logistic regression | error scaling in m | No clear effect |
Closest papers by meaning
- When to Forget? Complexity Trade-offs in Machine Unlearning (ICML 2025 · similarity 0.90)
- Hessian-Free Online Certified Unlearning (ICLR 2025 · similarity 0.90)
- Machine Unlearning under Overparameterization (NeurIPS 2025 · similarity 0.90)
- Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions (NeurIPS 2025 · similarity 0.89)
- Machine Unlearning in Low-Dimensional Feature Subspace (NeurIPS 2026 · similarity 0.89)
- Towards Source-Free Machine Unlearning (CVPR 2025 · similarity 0.89)
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.
