Research map / Learning theory and algorithms / Matrix and tensor methods
Exact Recovery of Hard Thresholding Pursuit
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 |
|---|---|---|---|
| Add debiasing step (S3, least-squares/loss minimization on selected support) to IHT, yielding HTP (ablation) | HTP vs IHT · Simulated linear regression and logistic regression, k=70 | Perc. of relaxed and exact support recovery success | Helped |
| Use sparsity level k slightly above true sparsity k̄ (relaxed k) in HTP | HTP · Simulated linear regression, k̄=50 | Perc. of relaxed and exact support success | Helped |
| Increase sample size n | HTP · Simulated linear and logistic regression | Perc. of relaxed/exact support recovery success | Helped |
| Relaxed support recovery is less sensitive to sparsity level k than exact recovery | HTP · Simulated linear regression | Perc. of success across k | No clear effect |
Closest papers by meaning
- On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit (ICML 2017 · similarity 0.93)
- Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm (ICML 2024 · similarity 0.86)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.86)
- Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization (ICML 2024 · similarity 0.85)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.84)
- Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence (ICML 2024 · 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.