Research map / Optimization / Nonconvex and smooth optimization
Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling
Xi Chen, Bo Jiang, Tianyi Lin, Shuzhong 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 |
|---|---|---|---|
| add Hessian sub-sampling with acceleration (SACR) versus the full-Hessian accelerated method ACR | accelerated adaptive cubic regularization · regularized logistic regression, 8 LIBSVM datasets | log norm of gradient vs epochs | Improved |
| use SACR instead of LBFGS, MLBFGS and SGD | regularized logistic regression solver · regularized logistic regression, 8 LIBSVM datasets | log norm of gradient vs epochs | Improved |
| add acceleration phase to sub-sampled cubic regularization (SACR versus SCR, SCR-KL, SCR-BGM) | sub-sampled cubic regularization · regularized logistic regression, 8 LIBSVM datasets | log norm of gradient vs epochs | Improved |
| switch from the accelerated phase to plain SCR near the optimum | SACR hybrid implementation · regularized logistic regression, 8 LIBSVM datasets | local convergence | Improved |
| compare SACR to other sub-sampled cubic methods once iterates reach the local region | sub-sampled cubic regularization · regularized logistic regression, 8 LIBSVM datasets | log norm of gradient vs epochs | No clear effect |
Closest papers by meaning
- Stochastic Variance-Reduced Cubic Regularization Methods (JMLR 2019 · similarity 0.91)
- Stochastic Cubic Regularization for Fast Nonconvex Optimization (NeurIPS 2018 · similarity 0.91)
- Convergence of Cubic Regularization for Nonconvex Optimization under KL Property (NeurIPS 2018 · similarity 0.90)
- Stochastic Variance-Reduced Cubic Regularized Newton Methods (ICML 2018 · similarity 0.90)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.89)
- AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning (NeurIPS 2026 · 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.
