Research map / Optimization / Nonconvex and smooth optimization
Approximate Newton Methods
Haishan Ye, Luo Luo, Zhihua Zhang
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 |
|---|---|---|---|
| increase sample size from 100 to 600 in Regularized Subsampled Newton | Regularized Subsampled Newton · Least squares (n=8000, d=5000) | iterations to precise solution: 8000 -> 1200 | Improved |
| use a large regularizer alpha when sample size is small, instead of a small one (ablation) | Regularized Subsampled Newton · Least squares (n=8000, d=5000) | convergence | Improved |
| make regularizer alpha too large (ablation) | Regularized Subsampled Newton · Least squares (n=8000, d=5000) | convergence speed | Hurt |
| use a small target rank in NewSamp when sample size is small (ablation) | NewSamp · Least squares (n=8000, d=5000) | convergence | Improved |
| drop Lipschitz continuity of the Hessian (Hinge-2 SVM with Subsampled Newton, 5% support vectors) | Subsampled Newton · Linear SVM on mushrooms, a9a, Covertype | convergence rate | No clear effect |
| use sketch size of several times d in Sketch Newton | Sketch Newton · Least squares (10000x54, kappa 1.8741e4) | convergence | Improved |
Closest papers by meaning
- Approximate Newton Methods and Their Local Convergence (ICML 2017 · similarity 0.99)
- Nesterov's Acceleration for Approximate Newton (JMLR 2020 · similarity 0.91)
- Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates (NeurIPS 2026 · similarity 0.87)
- Stochastic Newton Proximal Extragradient Method (NeurIPS 2024 · similarity 0.87)
- Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness (ICLR 2024 · similarity 0.87)
- Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits (NeurIPS 2025 · similarity 0.86)
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.
