Research map / Optimization / Implicit bias and generalization
A Nonconvex Approach for Phase Retrieval: Reshaped Wirtinger Flow and Incremental Algorithms
Huishuai Zhang, Yingbin Liang, Yuejie Chi
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 RWF (reshaped, lower-order loss) instead of TWF | batch gradient method · Real Gaussian, n=5000, m=8n | passes: 186 -> 72 | Improved |
| use RWF instead of WF | batch gradient method · Real Gaussian, n=5000, m=8n | time (s): 54.83 -> 12.66 | Improved |
| use RWF instead of AltMinPhase | batch method · Complex Gaussian, n=5000, m=8n | time (s): 9637 -> 122.4 | Improved |
| use mini-batch incremental updates (mini-batch IRWF 64) instead of batch RWF | RWF · Real Gaussian, n=5000, m=8n | time (s): 12.66 -> 8.076 | Improved |
| use incremental update instead of batch (IRWF vs RWF) | RWF · Real Gaussian, n=5000, m=8n | passes: 72 -> 9 | Improved |
| use IRWF update instead of ITWF | mini-batch incremental · Real Gaussian, n=5000, m=8n | time (s): 37.38 -> 8.076 | Improved |
| use incremental methods instead of batch methods | phase retrieval · Sample complexity, real/complex/CDP | success rate | Improved |
| use RWF instead of TWF (truncation) | batch methods · Real Gaussian sample complexity | success rate | Hurt |
| use RWF instead of TWF | batch methods · CDP sample complexity | success rate | Improved |
| use RWF instead of TWF | batch methods · Galaxy CDP, L=12 | passes: 190 -> 70 | Improved |
| use RWF initialization instead of WF, TWF, TAF | spectral initialization · m=6n, 50 power iterations | relative error after initialization | Improved |
| use RWF instead of TWF | batch methods · Poisson noise, alpha=1 and 0.001 | relative error | Improved |
Closest papers by meaning
- Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow (ICML 2016 · similarity 0.92)
- Reshaped Wirtinger Flow for Solving Quadratic System of Equations (NeurIPS 2016 · similarity 0.91)
- Fast, Sample-Efficient Algorithms for Structured Phase Retrieval (NeurIPS 2017 · similarity 0.89)
- A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval (NeurIPS 2020 · similarity 0.89)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.88)
- Convolutional Phase Retrieval (NeurIPS 2017 · similarity 0.88)
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.
