Semi-Supervised Empirical Risk Minimization: Using unlabeled data to improve prediction

Abstract

We present a general methodology for using unlabeled data to design semi supervised learning (SSL) variants of the Empirical Risk Minimization (ERM) learning process. Focusing on generalized linear regression, we analyze of the effectiveness of our SSL approach in improving prediction performance. The key ideas are carefully considering the null model as a competitor, and utilizing the unlabeled data to determine signal-noise combinations where SSL outperforms both supervised learning and the null model. We then use SSL in an adaptive manner based on estimation of the signal and noise. In the special case of linear regression with Gaussian covariates, we prove that the non-adaptive SSL version is in fact not capable of improving on both the supervised estimator and the null model simultaneously, beyond a negligible O(1/n) term. On the other hand, the adaptive model presented in this work, can achieve a substantial improvement over both competitors simultaneously, under a variety of settings. This is shown empirically through extensive simulations, and extended to other scenarios, such as non-Gaussian covariates, misspecified linear regression, or generalized linear regression with non-linear link functions.

arXiv comment39 pages, 4 figures

References in corpus (6)

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Semi-Supervised Learning with Deep Generative Models
• Confidence Intervals and Hypothesis Testing for High-Dimensional Regression
• Efficient and Adaptive Linear Regression in Semi-Supervised Settings
• Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learning
• De-Biasing The Lasso With Degrees-of-Freedom Adjustment

Cited by in corpus (1)

• Mixed Semi-Supervised Generalized-Linear-Regression with Applications to Deep-Learning and Interpolators