Research map / Learning theory and algorithms / Matrix and tensor methods
Accelerated Sparse Linear Regression via Random Projection
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 |
|---|---|---|---|
| approximate gradient with random-projection rank-k sketch instead of full data matrix | proximal gradient homotopy (PGH) · Synthetic, noise 0.01 | running time (s): 134.7 -> 2.4 | Helped |
| approximate gradient with random-projection sketch | PGH · Synthetic, noise 0.01 | error: 0.107 -> 0.111 | No clear effect |
| approximate gradient with random-projection sketch | PGH · Synthetic, noise 0.05 | error: 0.106 -> 0.127 | Hurt |
| approximate gradient with random-projection sketch | PGH · Synthetic, noise 0.05 | support set recovery: 0.988 -> 0.97 | Hurt |
| approximate gradient with random-projection sketch | PGH · MNIST regression | running time (s): 63.8 -> 0.7 | Helped |
| approximate gradient with random-projection sketch | PGH · MNIST regression | residual: 0.004 -> 0.005 | No clear effect |
| vary shrinkage rate eta from 0.91 to 0.95 (ablation) | SLRviaRP · Synthetic, noise 0.05 | error and residual | No clear effect |
Closest papers by meaning
- Sample Efficient Stochastic Gradient Iterative Hard Thresholding Method for Stochastic Sparse Linear Regression with Limited Attribute Observation (NeurIPS 2018 · similarity 0.89)
- Hardness and Algorithms for Robust and Sparse Optimization (ICML 2022 · similarity 0.88)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.86)
- Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks (NeurIPS 2024 · similarity 0.86)
- Optimization over Sparse Support-Preserving Sets: Two-Step Projection with Global Optimality Guarantees (ICML 2025 · similarity 0.86)
- Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming (NeurIPS 2024 · similarity 0.86)
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.