Semi-Supervised Linear Regression
From MaRDI portal
Abstract: We study a regression problem where for some part of the data we observe both the label variable () and the predictors (), while for other part of the data only the predictors are given. Such a problem arises, for example, when observations of the label variable are costly and may require a skilled human agent. When the conditional expectation is not exactly linear, one can consider the best linear approximation to the conditional expectation, which can be estimated consistently by the least squares estimates (LSE). The latter depends only on the labeled data. We suggest improved alternative estimates to the LSE that use also the unlabeled data. Our estimation method can be easily implemented and has simply described asymptotic properties.The new estimates asymptotically dominate the usual standard procedures under certain non-linearity condition of ; otherwise, they are asymptotically equivalent.The performance of the new estimator for small sample size is investigated in an extensive simulation study. A real data example of inferring homeless population is used to illustrate the new methodology.
Recommendations
Cites work
- scientific article; zbMATH DE number 3522963 (Why is no real title available?)
- scientific article; zbMATH DE number 3549966 (Why is no real title available?)
- An ancillarity paradox which appears in multiple linear regression
- Assumption Lean Regression
- Asymptotics in statistics: some basic concepts
- Efficient and adaptive linear regression in semi-supervised settings
- Graph-Based Semi-Supervised Learning and Spectral Kernel Design
- High-dimensional inference in misspecified linear models
- Models as approximations. I. Consequences illustrated with linear regression
- On efficient large margin semisupervised learning: method and theory
- On semi-supervised linear regression in covariate shift problems
- Semi-supervised inference: general theory and estimation of means
- Small area estimation of the homeless in Los Angeles: an application of cost-sensitive stochastic gradient boosting
- The conditionality principle in high-dimensional regression
- The use of unlabeled data in predictive modeling
- Using Least Squares to Approximate Unknown Regression Functions
Cited in
(25)- Solving the missing at random problem in semi-supervised learning: an inverse probability weighting method
- A General M-estimation Theory in Semi-Supervised Framework
- A general semi-parametric elliptical distribution model for semi-supervised learning
- Semi-Supervised Bilinear Subspace Learning
- Semi-supervised inference for case-control binary data under possibly mis-specified logistic models
- Approximating semi-structured data with different errors using support vector machine regression
- Extreme Value Statistics in Semi-Supervised Models
- Regularized semi-supervised least squares regression with dependent samples
- Prediction de-correlated inference: a safe approach for post-prediction inference
- Semi-Supervised Approaches to Efficient Evaluation of Model Prediction Performance
- Semi-supervised estimation of a single-index varying-coefficient model
- Semi-supervised inference for the high-dimensional quantile regression
- Improve efficiency of doubly robust estimator when propensity score is misspecified
- Efficient and multiply robust risk estimation under general forms of dataset shift
- Semi-supervised inference for nonparametric logistic regression
- Small area estimation of the homeless in Los Angeles: an application of cost-sensitive stochastic gradient boosting
- Mixed semi-supervised generalized linear regression with applications to deep learning and interpolators
- Semi-supervised U-statistics
- Assumption-lean and data-adaptive post-prediction inference
- Semi-supervised inference: general theory and estimation of means
- Efficient and adaptive linear regression in semi-supervised settings
- Semi-supervised linear regression: enhancing efficiency and robustness in high dimensions
- On the role of surrogates in the efficient estimation of treatment effects with limited outcome data
- Semi-supervised single- and multi-domain regression with multi-domain training
- On semi-supervised linear regression in covariate shift problems
This page was built for publication: Semi-Supervised Linear Regression
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6110736)
