The sample complexity of learning linear predictors with the squared loss

MaRDI QIDQ2788420zbMATH OpenFDO

Authors 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, http://jmlr.csail.mit.edu/papers/v16/shamir15a.html

zbMATH Keywords

distribution-free learninglinear predictorssample complexitysquared loss

Mathematics Subject Classification ID

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

Recommendations

• The importance of convexity in learning with squared loss
• scientific article; zbMATH DE number 2089350
• The optimal sample complexity of PAC learning
• scientific article; zbMATH DE number 1445318
• scientific article; zbMATH DE number 2087696

Cited in

(11)

• Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices
• Suboptimality of constrained least squares and improvements via non-linear predictors
• Distribution-free robust linear regression
• Finite sample performance of linear least squares estimation
• Characterizing the sample complexity of private learners
• scientific article; zbMATH DE number 2089350 (Why is no real title available?)
• Sample Complexity of Classifiers Taking Values in ℝ^Q, Application to Multi-Class SVMs
• Average stability is invariant to data preconditioning. Implications to exp-concave empirical risk minimization
• Worst-case bounds for the logarithmic loss of predictors
• Sample complexity of the sign-perturbed sums method
• On the complexity of proper distribution-free learning of linear classifiers

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)