Research map / Learning theory and algorithms / Matrix and tensor methods
Local and Global Linear Convergence of General Low-Rank Matrix Recovery Problems
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 |
|---|---|---|---|
| Use the perturbed gradient descent method with local improvement under the δ-RIP2r condition | Symmetric low-rank matrix recovery · Symmetric low-rank matrix recovery | iterations for ϵ-accuracy: O(log(1/ϵ)) | Helped |
| Use the perturbed gradient descent method with local improvement under the δ-RIP2r condition | Asymmetric low-rank matrix recovery · Asymmetric low-rank matrix recovery | iterations for ϵ-accuracy: O(log(1/ϵ)) | Helped |
| Use the PL inequality instead of the stronger local regularity condition | Factored low-rank matrix recovery · Local convergence region | RIP assumption and region size | Helped |
| Perturb gradient steps and switch to local gradient descent once near a minimizer | Symmetric low-rank matrix recovery · Symmetric low-rank matrix recovery | convergence rate: O(log(1/ϵ)) | Helped |
Closest papers by meaning
- Sharp Restricted Isometry Property Bounds for Low-Rank Matrix Recovery Problems with Corrupted Measurements (AAAI 2022 · similarity 0.93)
- Global Optimality of Local Search for Low Rank Matrix Recovery (NeurIPS 2016 · similarity 0.92)
- A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery (ICML 2018 · similarity 0.90)
- No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis (ICML 2017 · similarity 0.89)
- Symmetric Matrix Completion with ReLU Sampling (ICML 2024 · similarity 0.89)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 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.