Research map / Learning theory and algorithms / Matrix and tensor methods
A Continuous-Time Mirror Descent Approach to Sparse 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 |
|---|---|---|---|
| Use continuous-time mirror descent with the hypentropy mirror map on the unregularized square-loss risk | Sparse phase retrieval · Sparse phase retrieval, Gaussian measurements | sample complexity: \widetilde{\mathcal{O}}(k^2) | Helped |
| Decrease the hypentropy parameter β from 10^{-6} to 10^{-14} (ablation) | Hadamard Wirtinger flow · 10-sparse signal in R^{50000}, 1000 Gaussian measurements | precision reached during linear convergence | Helped |
| Decrease the hypentropy parameter β (ablation) | Hadamard Wirtinger flow · 10-sparse signal in R^{50000}, 1000 Gaussian measurements | warm-up duration: 10^{-6} to 10^{-14} | Hurt |
Closest papers by meaning
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.89)
- Implicit Regularization in Matrix Sensing via Mirror Descent (NeurIPS 2021 · similarity 0.89)
- Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors (NeurIPS 2021 · similarity 0.89)
- Exponential Spectral Pursuit: An Effective Initialization Method for Sparse Phase Retrieval (ICML 2024 · similarity 0.87)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.86)
- Implicit Bias of Mirror Flow on Separable Data (NeurIPS 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.