Semi-supervised empirical risk minimization: using unlabeled data to improve prediction

DOI10.1214/22-EJS1985MaRDI QIDQ2136649

Oren Yuval, Saharon Rosset

Publication date: 11 May 2022

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.00606

zbMATH Keywords

generalized linear modelpredictive modelingsemi-supervised regression

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Trace inequalities for positive definite matrix power products
• Behaviour of third order terms in quadratic approximations of LR- statistics in multivariate generalized linear models
• On the prediction loss of the Lasso in the partially labeled setting
• Debiasing the Lasso: optimal sample size for Gaussian designs
• Semi-supervised inference: general theory and estimation of means
• Efficient and adaptive linear regression in semi-supervised settings
• An ancillarity paradox which appears in multiple linear regression
• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• From Fixed-X to Random-X Regression: Bias-Variance Decompositions, Covariance Penalties, and Prediction Error Estimation
• A note on the expected value of an inverse matrix
• A Paradoxical Result in Estimating Regression Coefficients

This page was built for publication: Semi-supervised empirical risk minimization: using unlabeled data to improve prediction