Research map / Learning theory and algorithms / Matrix and tensor methods
Phase Retrieval Under a Generative Prior
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 a generative prior instead of wavelet sparsity-based recovery | phase retrieval on MNIST · MNIST test set | mean SSIM: 200 measurements vs 1000 measurements or more | Helped |
| use a generative prior instead of wavelet sparsity-based recovery | phase retrieval on MNIST · MNIST test set | per-pixel reconstruction error: 200 measurements comparable to 750 measurements or more | Helped |
| use a generative prior rather than sparse phase retrieval | DPR · synthetic Gaussian signals | empirical success rate | Helped |
| reduce SPARTA sparsity from 10 to 3 | SPARTA · synthetic Gaussian signals | empirical success rate | Mixed |
| use a generative prior rather than sparse phase retrieval | DPR · CelebA test set | reconstruction fidelity: 500 measurements | Helped |
| increase the number of measurements | DPR with the MNIST VAE · MNIST test set | per-pixel reconstruction error | No clear effect |
Closest papers by meaning
- Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors (NeurIPS 2021 · similarity 0.93)
- Misspecified Phase Retrieval with Generative Priors (NeurIPS 2022 · similarity 0.91)
- prDeep: Robust Phase Retrieval with a Flexible Deep Network (ICML 2018 · similarity 0.89)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.89)
- How many measurements are enough? Bayesian recovery in inverse problems with general distributions (NeurIPS 2025 · similarity 0.87)
- Sparse Bayesian Generative Modeling for Compressive Sensing (NeurIPS 2024 · 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.