Research map / Learning theory and algorithms / Matrix and tensor methods
Fast Regression for Structured Inputs
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 ℓ_{p/2^r} Lewis weight sampling instead of uniform sampling | Vandermonde ℓ_p regression · Synthetic Vandermonde data | relative error | Helped |
| Use ℓ_{p/2^r} Lewis weight sampling instead of uniform sampling | Unstructured ℓ_p regression · Synthetic unstructured matrix, n=25,000, d=10, p=6 | relative error | Helped |
| Vary p while using ℓ_{p/2^r} Lewis weight sampling | Vandermonde ℓ_p regression · Synthetic Vandermonde data, m=1000 | relative error | Mixed |
| Increase the number of sampled rows using ℓ_{p/2^r} Lewis weight sampling | Unstructured ℓ_p regression · Synthetic unstructured matrix, p=6 | relative error | Helped |
Closest papers by meaning
- A Nearly-Optimal Bound for Fast Regression with $\ell_\infty$ Guarantee (ICML 2023 · similarity 0.89)
- Improved $\ell_{p}$ Regression via Iteratively Reweighted Least Squares (ICLR 2026 · similarity 0.88)
- Coresets for Multiple $\ell_p$ Regression (ICML 2024 · similarity 0.86)
- Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation (ICML 2024 · similarity 0.85)
- Turnstile $\ell_p$ leverage score sampling with applications (ICML 2024 · similarity 0.85)
- Agnostic Sample Compression Schemes for Regression (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.