2013/06/24 by Brian McWilliams, David Balduzzi, McWilliams, Brian +3
Computer Science · Mathematics · #Artificial intelligence #Artificial neural network #Canonical correlation #Computer science #Correlation #Domain Adaptation and Few-Shot Learning #Estimator #FOS: Computer and information sciences #Face and Expression Recognition #Kernel (algebra) #Kernel regression #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Machine learning #Mathematics #Pattern recognition (psychology) #Random forest #Regression #Regression analysis #Semi-supervised learning #Statistics #Supervised learning #Variance (accounting) #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1306.5554
15 pages, 3 figures, 6 tables
openalex publication_date 2013/06/24 · arxiv created 2013/11/05 · arxiv updated 2013/11/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper presents Correlated Nystrom Views (XNV), a fast semi-supervised algorithm for regression and classification. The algorithm draws on two main ideas. First, it generates two views consisting of computationally inexpensive random features. Second, XNV applies multiview regression using Canonical Correlation Analysis (CCA) on unlabeled data to bias the regression towards useful features. It has been shown that, if the views contains accurate estimators, CCA regression can substantially reduce variance with a minimal increase in bias. Random views are justified by recent theoretical and empirical work showing that regression with random features closely approximates kernel regression, implying that random views can be expected to contain accurate estimators. We show that XNV consistently outperforms a state-of-the-art algorithm for semi-supervised learning: substantially improving predictive performance and reducing the variability of performance on a wide variety of real-world datasets, whilst also reducing runtime by orders of magnitude.