Research map / Optimization / Nonconvex and smooth optimization
Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems
Yair Carmon, John C. Duchi
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 |
|---|---|---|---|
| increase Krylov subspace dimension to about 20 Lanczos iterations | Krylov subspace solution · 5,000 random cubic-regularization problems, d=10^6 | relative accuracy: about 10% accuracy at 20 iterations | Improved |
| increase Krylov subspace dimension to 100 iterations | Krylov subspace solution · 5,000 random cubic-regularization problems, d=10^6 | relative accuracy: better than 1% at 100 iterations | Improved |
| larger subspace dimension t at or above sqrt of condition number | Krylov subspace solution · random cubic-regularization problems | approximation error | Improved |
| subspace dimension t much smaller than sqrt of condition number | Krylov subspace solution · random cubic-regularization problems | approximation error: decays as t^-2 | Improved |
| perturbation scheme with tuned sigma instead of joint subspace randomization (ablation) | Randomized Krylov method · hard-case instances (kappa=1) | convergence speed to a fixed target accuracy | Improved |
| perturbation scheme with fixed sigma instead of joint subspace randomization (ablation) | Randomized Krylov method · hard-case instances (kappa=1) | final accuracy | Hurt |
Closest papers by meaning
- Nearly Optimal Approximation of Matrix Functions by the Lanczos Method (NeurIPS 2024 · similarity 0.86)
- Entrywise convergence of iterative methods for eigenproblems (NeurIPS 2020 · similarity 0.86)
- Quadratic Optimization with Orthogonality Constraints: Explicit Lojasiewicz Exponent and Linear Convergence of Line-Search Methods (ICML 2016 · similarity 0.85)
- Fast and Stable Gradient Approximation for Bilinear Forms of Hermitian Matrix Functions (NeurIPS 2026 · similarity 0.83)
- LancBiO: Dynamic Lanczos-aided Bilevel Optimization via Krylov Subspace (ICLR 2025 · similarity 0.82)
- Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization (ICLR 2025 · similarity 0.82)
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.
