Research map / Learning theory and algorithms / Sample complexity
Improved Leverage Score Sampling for Constrained Active Linear Regression
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies active constrained linear regression, where the solver queries entries of the response vector b to approximately minimize ||Ax-b||^2 over a constraint set C with few queries.
Problem
Constrained linear regression with query access to the response vector b: find an approximate constrained least-squares solution using as few queries to b as possible.
Approach
Improves leverage score sampling for the constrained active setting; the abstract provides only the problem setup, so the specific technique is not stated.
Closest papers by meaning
- Improved Active Learning via Dependent Leverage Score Sampling (ICLR 2024 · similarity 0.90)
- Online Active Linear Regression via Thresholding (AAAI 2017 · similarity 0.88)
- On Fast Leverage Score Sampling and Optimal Learning (NeurIPS 2018 · similarity 0.88)
- Ridge Regression and Provable Deterministic Ridge Leverage Score Sampling (NeurIPS 2018 · similarity 0.87)
- Importance Sampling for Nonlinear Models (ICML 2025 · similarity 0.85)
- Turnstile $\ell_p$ leverage score sampling with applications (ICML 2024 · 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.