Research map / Optimization / Nonconvex and smooth optimization
Sub-sampled Cubic Regularization for Non-convex Optimization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 sub-sampled gradient and Hessian estimates in cubic regularization instead of full-data estimates | Cubic regularization (SCR) · a9a, covtype, higgs | computation time | Helped |
| Use sub-sampled gradient and Hessian estimates in cubic regularization instead of full-data estimates | Cubic regularization (SCR) · a9a, covtype, higgs | suboptimality | No clear effect |
| Use the proposed iteration-dependent sampling scheme instead of linearly increasing sample sizes (ablation) | SCR · a9a, covtype, gaussian | suboptimality | Helped |
| Use the proposed iteration-dependent sampling scheme instead of exponentially increasing sample sizes (ablation) | SCR · a9a, covtype, gaussian | suboptimality | Helped |
| Use Newton's method instead of SCR | Optimization of logistic regression · a9a, covtype, higgs | computation time | Mixed |
| Use BFGS instead of SCR | Non-convex logistic regression · higgs | optimization completion | Hurt |
| Use Newton's method instead of SCR | Non-convex logistic regression · covtype | optimization completion | Hurt |
Closest papers by meaning
- Sub-sampled Newton Methods with Non-uniform Sampling (NeurIPS 2016 · similarity 0.90)
- Efficient Hyper-parameter Optimization with Cubic Regularization (NeurIPS 2023 · similarity 0.89)
- Stochastic Variance-Reduced Cubic Regularized Newton Methods (ICML 2018 · similarity 0.88)
- Stochastic Cubic Regularization for Fast Nonconvex Optimization (NeurIPS 2018 · similarity 0.88)
- AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning (NeurIPS 2026 · similarity 0.86)
- Trust Region Methods for Nonconvex Stochastic Optimization beyond Lipschitz Smoothness (AAAI 2024 · 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.