Research map / Learning theory and algorithms / Matrix and tensor methods
Partial Hard Thresholding: Towards A Principled Analysis of Support 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 |
|---|---|---|---|
| Use RIP-free condition with sparsity parameter k = O(s + κ^2 min{s, r}) instead of k = O(κ s) for PHT(r) | PHT(r) (partial hard thresholding) · theoretical support recovery analysis | required sparsity parameter k / support inclusion | Helped |
| Increase freedom parameter r (more replacements per iteration) (ablation) | PHT(r) iteration count · simulated compressed sensing, d=200, N=200 | iteration number | Helped |
| Increase freedom parameter r beyond about 5 (ablation) | PHT(r) iteration count · simulated compressed sensing, s=10, N varied | iteration number | No clear effect |
| Increase freedom parameter r (ablation) | PHT(r) success percentage · simulated compressed sensing, s=10, varying measurements | percentage of success | No clear effect |
Closest papers by meaning
- On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit (ICML 2017 · similarity 0.91)
- Exact Recovery of Hard Thresholding Pursuit (NeurIPS 2016 · similarity 0.89)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.87)
- Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm (ICML 2024 · similarity 0.86)
- A Fast and Provable Algorithm for Sparse Phase Retrieval (ICLR 2024 · similarity 0.86)
- Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing (NeurIPS 2026 · 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.