Research map / Optimization / Nonconvex and smooth optimization
A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate
Slavomir Hanzely, Dmitry Kamzolov, Dmitry Pasechnyuk, Alexander Gasnikov, Peter Richtárik, Martin Takáč
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 AICN (damped Newton with explicit stepsize) instead of fixed-stepsize Damped Newton | AICN · logistic regression on a9a, start x0 = 10*ones | convergence per iteration and per time | Improved |
| use AICN instead of Cubic Newton | AICN · logistic regression on a9a | wall-clock time | Improved |
| use AICN instead of Cubic Newton | AICN · second-order lower bound function (d = 20) | convergence per iteration | Hurt |
| use AICN instead of Damped Newton with fixed stepsize | AICN · second-order lower bound function (d = 20) | convergence per iteration | Improved |
Closest papers by meaning
- Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates (NeurIPS 2026 · similarity 0.87)
- Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance (NeurIPS 2025 · similarity 0.86)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.86)
- Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates (AAAI 2024 · similarity 0.85)
- Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search (NeurIPS 2024 · similarity 0.84)
- Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning (NeurIPS 2025 · similarity 0.84)
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.
