Research map / Learning theory and algorithms / Matrix and tensor methods
Provable Non-convex Phase Retrieval with Outliers: Median TruncatedWirtinger Flow
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 |
|---|---|---|---|
| replace sample mean truncation with sample median truncation (median-TWF) | truncated Wirtinger flow · sparse arbitrary outliers, n=1000, m=8000 | success rate of exact recovery | Helped |
| use median-based truncation instead of mean-based truncation | median-TWF vs TWF in noise-free case · noise-free phase retrieval | phase transition location | Hurt |
| add sparse arbitrary outliers without robust handling (TWF) | TWF · sparse outliers, n=1000, m=8000 | success rate of exact recovery | Hurt |
| trimmed-mean truncation (trimean-TWF) that requires knowing outlier fraction | TWF · sparse outliers, n=1000, m=8000 | success rate of exact recovery | Mixed |
| add dense bounded noise on top of sparse outliers with median-TWF | median-TWF · uniform noise plus outliers, relative error | relative error vs iteration | No clear effect |
Closest papers by meaning
- Reshaped Wirtinger Flow for Solving Quadratic System of Equations (NeurIPS 2016 · similarity 0.87)
- Sparse blind deconvolution via thresholded Wirtinger flow (NeurIPS 2026 · similarity 0.87)
- A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval (NeurIPS 2020 · similarity 0.87)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.84)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.84)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 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.