Research map / Learning theory and algorithms / Matrix and tensor methods
Iteratively Reweighted Least Squares for Basis Pursuit with Global Linear Convergence Rate
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 |
|---|---|---|---|
| adversarial initial weights (large on the true support) instead of uniform weights (ablation) | IRLS for basis pursuit · N=16000 sparse recovery | support identification iteration: 30 -> 39 | Hurt |
| adversarial initial weights instead of uniform weights (ablation) | IRLS for basis pursuit · N=16000 sparse recovery | instantaneous linear convergence factor mu(k): mu(1)=0.980, stabilizing around 0.79 | Hurt |
| adversarial initialization affects eventual behavior (ablation) | IRLS for basis pursuit · N=16000 sparse recovery | eventual convergence behavior | No clear effect |
Closest papers by meaning
- Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks (NeurIPS 2024 · similarity 0.91)
- Improved Convergence for $\ell_1$ and $\ell_∞$ Regression via Iteratively Reweighted Least Squares (ICML 2019 · similarity 0.90)
- Smooth Bilevel Programming for Sparse Regularization (NeurIPS 2021 · similarity 0.90)
- Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares (NeurIPS 2023 · similarity 0.89)
- Iterative Regularization with k-support Norm: An Important Complement to Sparse Recovery (AAAI 2024 · similarity 0.87)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · 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.