Research map / Optimization / Nonconvex and smooth optimization
Newton Method Revisited: Global Convergence Rates up to $O(1/k^3)$ for Stepsize Schedules and Linesearch Procedures
Slavomir Hanzely, Farshed Abdukhakimov, 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 Root Newton stepsize instead of AICN | Root Newton · Logistic regression and polytope feasibility | convergence speed | No clear effect |
| use the universal Newton backtracking method instead of Super-universal Newton | Universal Newton · Logistic regression and polytope feasibility | convergence speed | Improved |
| vary the exponent beta of the regularization term (ablation) | Universal Newton and Super-universal Newton · Logistic regression and polytope feasibility | convergence speed | No clear effect |
| use GRLS or Greedy Newton linesearch instead of Armijo or fixed-stepsize Newton | Newton method · Logistic regression and polytope feasibility | convergence speed | Improved |
| use GRLS linesearch instead of other linesearches | Newton method · Rosenbrock function (nonconvex, 5 random initializations) | convergence | Improved |
| use a first-order gradient method instead of Newton-type methods | Gradient Method · Logistic regression and polytope feasibility | per-iteration convergence | Hurt |
Closest papers by meaning
- Skip the Hessian, Keep the Rates: Globalized Semismooth Newton with Lazy Hessian Updates (NeurIPS 2026 · similarity 0.89)
- A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees (NeurIPS 2025 · similarity 0.88)
- Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search (NeurIPS 2024 · similarity 0.88)
- Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness (ICML 2025 · similarity 0.87)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.87)
- Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance (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.
