Research map / Learning theory and algorithms / Matrix and tensor methods
One-Step Estimator for Permuted Sparse Recovery
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 |
|---|---|---|---|
| Keep more than one non-zero entry per column in thres(X^T Y) (keeping more non-zero elements) (ablation) | permutation estimator thresholding step · synthetic, n=100, p=500, h=25, k=5, srank=100 | correct permutation recovery vs SNR | Hurt |
| Increase sample number n beyond a threshold (with fixed srank(B)) (ablation) | permutation recovery · noiseless, p=200, k=5, h=25 | permutation recovery rate | Hurt |
| Increase sparsity k from 10 to 20 | permutation recovery · Gaussian sensing, n=100, p=500, srank=200 | SNR needed for correct permutation: SNR 1.4 -> 4 | Hurt |
| Use the proposed estimator (thresholded LAP permutation recovery) with insufficient samples n << p | permutation recovery · Gaussian and Rademacher sensing, n=100/150, p=500/600 | correct permutation recovery probability | Helped |
| Apply permutation recovery (Algorithm 1 step 1) before Lasso on MNIST block-diagonal signal (ablation) | image reconstruction from permuted measurements · MNIST block-diagonal sparse signal, n=100, sigma^2=1 | visual reconstruction quality | Helped |
Closest papers by meaning
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.91)
- Support Recovery of Sparse Signals from a Mixture of Linear Measurements (NeurIPS 2021 · similarity 0.88)
- Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements (ICML 2025 · similarity 0.87)
- Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing (NeurIPS 2026 · similarity 0.85)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · similarity 0.85)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.85)
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.