Research map / Optimization / Implicit bias and generalization
Convolutional Phase Retrieval
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 |
|---|---|---|---|
| Increase ||Cx|| (signal sparser/flatter in Fourier domain) for fixed n (ablation) | Gradient descent with spectral initialization · Synthetic signals, n=1000 | sample complexity needed for exact recovery | Hurt |
| Use smoothing weight b = zeta_sigma2(y) (Gaussian smoothing) in the objective | Analysis of convolutional phase retrieval objective · Theoretical analysis | approximation error ||h - zeta*psi||_inf in decoupling bound | Helped |
| Replace generic i.i.d. Gaussian measurements with random circulant convolution measurements | Phase retrieval sample complexity · Theory | sample complexity scaling | Mixed |
| Use fast FFT-based matrix-vector products instead of dense Gaussian matrices | Gradient descent for convolutional phase retrieval · Real image experiment, 200x300, m=5n log n | memory and per-iteration computation | Helped |
Closest papers by meaning
- Blind Deconvolutional Phase Retrieval via Convex Programming (NeurIPS 2018 · similarity 0.91)
- Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors (NeurIPS 2021 · similarity 0.90)
- Phase retrieval in high dimensions: Statistical and computational phase transitions (NeurIPS 2020 · similarity 0.89)
- Universality in Learning from Linear Measurements (NeurIPS 2019 · similarity 0.89)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.88)
- Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval (ICML 2024 · similarity 0.86)
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.