Research map / Optimization / Optimizers
Gradient Descent Meets Shift-and-Invert Preconditioning for Eigenvector Computation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| add shift-and-invert preconditioning to Riemannian gradient descent (constant step-size) (ablation) | rgEIGS · Synthetic data (n=1000) | convergence speed (relative function error vs time) | Helped |
| replace adaptive step-size (SI-PM) with hand-tuned constant step-size in shift-and-invert Riemannian GD (ablation) | SI-rgEIGS · Synthetic data (n=1000) | convergence speed (time) | Helped |
| use Barzilai-Borwein step-sizes instead of the adaptive step-size of the shift-and-inverted power method | SI-rgEIGS · Real sparse matrices (hangGlider5, Boeing35, indef_d, indef_a, dimacs10_ct, dimacs10_nv) | convergence speed (time) | Helped |
Closest papers by meaning
- How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization (ICLR 2024 · similarity 0.86)
- Convergence and Complexity Guarantee for Inexact First-order Riemannian Optimization Algorithms (ICML 2024 · similarity 0.86)
- Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space (NeurIPS 2025 · similarity 0.86)
- Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions (ICML 2024 · similarity 0.85)
- Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives (NeurIPS 2026 · similarity 0.85)
- Fast and Stable Gradient Approximation for Bilinear Forms of Hermitian Matrix Functions (NeurIPS 2026 · 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.
