Research map / Optimization / Nonconvex and smooth optimization
Stochastic Variance-Reduced Cubic Regularization Methods
Dongruo Zhou, Pan Xu, Quanquan Gu
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 SVRC instead of trust-region, adaptive cubic, subsampled cubic, gradient cubic and stochastic cubic baselines | cubic regularization · a9a, ijcnn1, covtype (nonconvex logistic regression and nonlinear least squares) | function value gap vs second-order oracle calls | Improved |
| use SVRC instead of Adaptive Cubic, nonlinear least squares | cubic regularization · covtype (nonlinear least squares) | function value gap vs epochs | Mixed |
| use Lite-SVRC instead of all baselines including SVRC | cubic regularization · a9a, ijcnn1, covtype (nonconvex logistic regression) | function value gap vs Hessian samples and CPU time | Improved |
| use Lite-SVRC instead of SVRC-without (Wang et al.) | variance-reduced cubic regularization · a9a, ijcnn1, covtype | Hessian sample complexity | Improved |
| use Lite-SVRC instead of baselines, nonlinear least squares | cubic regularization · a9a, ijcnn1, covtype (nonlinear least squares) | function value gap vs Hessian samples and CPU time | Improved |
Closest papers by meaning
- Stochastic Variance-Reduced Cubic Regularized Newton Methods (ICML 2018 · similarity 0.98)
- Stochastic Cubic Regularization for Fast Nonconvex Optimization (NeurIPS 2018 · similarity 0.93)
- Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling (JMLR 2022 · similarity 0.91)
- Convergence of Cubic Regularization for Nonconvex Optimization under KL Property (NeurIPS 2018 · similarity 0.89)
- Stochastic Subspace Cubic Newton Method (ICML 2020 · similarity 0.89)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.87)
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.
