Research map / Learning theory and algorithms / Sample complexity
Efficient algorithms for linear regression with heteroskedastic errors
Sergei Vassilvitskii, Silvio Lattanzi, Aditya Bhaskara, Siddhant Chaudhary
Read the paperCheck your idea against 137,217 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 linear regression with heteroskedastic noise across n sources with unknown variances, focusing on the subset-selection-style estimation problem (abstract truncated).
Problem
Linear regression where n sources each give a linear measurement of an unknown d-dimensional parameter with unknown, possibly unequal noise variances; the abstract is truncated at the classic subset-selection formulation.
Approach
Abstract truncated; the stated focus is on efficient algorithms for the classic heteroskedastic subset-selection formulation of linear regression. Specific technique not stated in the available text.
Limitations
- Only a truncated abstract was available; full method and results unknown
Closest papers by meaning
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.87)
- Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination (NeurIPS 2025 · similarity 0.87)
- Distributed High-Dimensional Quantile Regression: Estimation Efficiency and Support Recovery (ICML 2024 · similarity 0.85)
- A Skewness-Based Criterion for Addressing Heteroscedastic Noise in Causal Discovery (ICLR 2025 · similarity 0.85)
- Regularized least squares learning with heavy-tailed noise is minimax optimal (NeurIPS 2025 · similarity 0.85)
- Robustness Auditing for Linear Regression: To Singularity and Beyond (ICLR 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.
