2009 · 58 citations · 17 references
ComputingAstronomyComputer ScienceMachine LearningScientific ComputingStatistical LearningComputational AstrophysicsGaussian Process ModelingGaussian ProcessesNumerical AlgorithmsNumerical AnalysisNumerical AstrophysicsGalaxy Redshift DistributionGalaxy Redshift SurveysGaussian Process FilteringNumerical Stability Analysis
The use of Gaussian processes can be an effective approach to prediction in a supervised learning environment. For large data sets, the standard Gaussian process approach requires solving very large systems of linear equations and approximations are required for the calculations to be practical. We will focus on the subset of regressors approximation technique. We will demonstrate that there can be numerical instabilities in a well known implementation of the technique. We discuss alternate implementations that have better numerical stability properties and can lead to better predictions. Our results will be illustrated by looking at an application involving prediction of galaxy redshift from broadband spectrum data.
17
The Sloan Digital Sky Survey: Technical Summary
Donald G. York, Jennifer Adelman, John E. Anderson et al. · The Astronomical Journal · 2000 · 10.5K citations · Full text
Natural Sciences, Astronomy, Physics +14
Introduction to Linear Regression Analysis.
Renato Assunção, Paul D. Sampson, Douglas C. Montgomery et al. · Journal of the American Statistical Association · 1993 · 5.4K citations
Networks for approximation and learning
Tomaso Poggio, Federico Girosi · Proceedings of the IEEE · 1990 · 3.3K citations
Numerical methods for least squares problems
Choice Reviews Online · 1996 · 3.1K citations
Choice Reviews Online · 2008 · 2.8K citations