Research map / Learning theory and algorithms / Sample complexity
Agnostic Estimation for Misspecified Phase Retrieval Models
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 |
|---|---|---|---|
| optional refinement step (Algorithm 2) applied after Algorithm 1 | agnostic two-step MPR estimator · simulations, models (2.3)-(2.5), d=200 and 400 | estimation error ||β̂−β*||2 | Helped |
| sparse SDP warm start replaced by second-step ℓ1 least squares on augmented outcome | Algorithm 1 second step · simulations, models (2.3)-(2.5) | estimation error ||β̂−β*||2 | Helped |
| agnostic estimator compared to TWF on noisy phase retrieval model (2.3) | proposed procedure vs TWF · simulations, model (2.3) | estimation error ||β̂−β*||2 | Mixed |
Closest papers by meaning
- Misspecified Phase Retrieval with Generative Priors (NeurIPS 2022 · similarity 0.92)
- Phase retrieval in high dimensions: Statistical and computational phase transitions (NeurIPS 2020 · similarity 0.88)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.87)
- Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors (NeurIPS 2021 · similarity 0.87)
- Convolutional Phase Retrieval (NeurIPS 2017 · similarity 0.87)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 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.