Research map / Federated learning and privacy / Differential privacy
Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
Jiaqi Liu, Jian Lou, Zhan Qin, Kui Ren
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 the total Hessian, including indirect Hessian terms, rather than a conventional direct-Hessian Newton update | Minimax unlearning · SC-SC minimax unlearning | unlearning certification | Improved |
| Avoid recomputing the updated total Hessian during unlearning (ablation) | Certified Minimax Unlearning · SC-SC minimax unlearning | computational cost | Improved |
| Use the efficient update without total-Hessian recomputation (ablation) | Certified Minimax Unlearning · SC-SC minimax unlearning | population primal-dual risk | Improved |
| Extend the certified method to convex-concave losses by regularizing the objective (ablation) | Certified Minimax Unlearning · Convex-concave minimax unlearning | deletion capacity: c \cdot \frac{n\sqrt{\epsilon}}{(d\log(1/\delta))^{1/4}} | Improved |
Closest papers by meaning
- Hessian-Free Online Certified Unlearning (ICLR 2025 · similarity 0.92)
- Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions (NeurIPS 2025 · similarity 0.90)
- Machine Unlearning under Overparameterization (NeurIPS 2025 · similarity 0.90)
- Certified Machine Unlearning via Noisy Stochastic Gradient Descent (NeurIPS 2024 · similarity 0.89)
- When to Forget? Complexity Trade-offs in Machine Unlearning (ICML 2025 · similarity 0.88)
- Certified Unlearning for Neural Networks (ICML 2025 · similarity 0.88)
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.
