The sample complexity of learning linear predictors with the squared loss

zbMATH Open1351.68233arXiv1406.5143MaRDI QIDQ2788420FDOQ2788420

Ohad Shamir

Publication date: 19 February 2016

Published in: Journal of Machine Learning Research (JMLR) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1406.5143

zbMATH Keywords

sample complexitylinear predictorssquared lossdistribution-free learning

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05)

Cited In (8)

• Suboptimality of constrained least squares and improvements via non-linear predictors
• Finite sample performance of linear least squares estimation
• Distribution-free robust linear regression
• Title not available (Why is that?)
• Characterizing the sample complexity of private learners
• Worst-case bounds for the logarithmic loss of predictors
• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Sample Complexity of Classifiers Taking Values in ℝ^Q, Application to Multi-Class SVMs

This page was built for publication: The sample complexity of learning linear predictors with the squared loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2788420)