Research map / Optimization / Nonconvex and smooth optimization
Adaptive Negative Curvature Descent with Applications in Non-convex Optimization
Mingrui Liu, Zhe Li, Xiaoyu Wang, Jinfeng Yi, Tianbao Yang
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 |
|---|---|---|---|
| make the negative curvature approximation noise adaptive to gradient magnitude (AdaNCD) instead of fixed epsilon2/2 (ablation) | AdaNCG · cubic regularization, regularized nonlinear least squares, one-hidden-layer NN | objective value vs oracle calls | Improved |
| make the negative curvature approximation noise adaptive to gradient magnitude (AdaNCD) instead of fixed epsilon2/2 (ablation) | AdaNCG+ (vs NCD-AG) · cubic regularization, regularized nonlinear least squares, one-hidden-layer NN | objective value vs oracle calls | Improved |
| make the negative curvature approximation noise adaptive (AdaNCD) in SCSG-based stochastic algorithm (ablation) | AdaNCD-SCSG (vs NCD-SCSG) · stochastic cubic regularization, nonlinear least squares, NN | objective value vs oracle calls | Improved |
| use AdaNCG (guaranteed decrease every iteration) instead of AdaNCG+ (switch to accelerated gradient) | deterministic adaptive algorithms · tested tasks | objective value vs oracle calls | Improved |
| use AdaNCD-SCSG instead of S-AdaNCG | stochastic adaptive algorithms · tested tasks | objective value vs oracle calls | Improved |
Closest papers by meaning
- First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time (NeurIPS 2018 · similarity 0.90)
- Adaptive Proximal Gradient Method for Convex Optimization (NeurIPS 2024 · similarity 0.88)
- From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization (NeurIPS 2026 · similarity 0.87)
- An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds (NeurIPS 2025 · similarity 0.86)
- SERENA: A Unified Stochastic Recursive Variance Reduced Gradient Framework for Riemannian Non-Convex Optimization (ICML 2025 · similarity 0.86)
- Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization (ICML 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.
