Research map / Optimization / Nonconvex and smooth optimization
Solving Random Systems of Quadratic Equations via Truncated Generalized Gradient Flow
Gang Wang, Georgios Giannakis
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 |
|---|---|---|---|
| replace TWF refinement with TGGF truncation and update rule, same truncated spectral initialization (ablation) | TWF · Gaussian phase retrieval, Fig. 1 | relative error | Improved |
| use orthogonality-promoting initialization instead of spectral and truncated spectral (ablation) | initialization · noiseless and noisy, m/n=6, n up to 10,000 | relative error | Improved |
| use TGGF instead of TWF in sample complexity | TGGF · real Gaussian, n=1000 | m/n needed for exact recovery: 5 -> 3 | Improved |
| use TGGF instead of WF in sample complexity | TGGF · real Gaussian, n=1000 | m/n needed for exact recovery: 7 -> 3 | Improved |
| TGGF at m/n=2, near information limit | TGGF · real Gaussian, n=1000 | success rate: over 50% | Improved |
| TGGF versus TWF running time | TGGF · phase retrieval | running time | Improved |
| amplitude-based cost instead of intensity-based cost | gradient stage · phase retrieval | performance | Improved |
Closest papers by meaning
- Solving Most Systems of Random Quadratic Equations (NeurIPS 2017 · similarity 0.88)
- Reshaped Wirtinger Flow for Solving Quadratic System of Equations (NeurIPS 2016 · similarity 0.86)
- Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks (NeurIPS 2024 · similarity 0.85)
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions (NeurIPS 2024 · similarity 0.85)
- Scalable First-order Method for Certifying Optimal k-Sparse GLMs (ICML 2025 · similarity 0.84)
- Nonasymptotic Analysis of Stochastic Gradient Descent with the Richardson–Romberg Extrapolation (ICLR 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.
