Publication Abstracts

Foster et al. 2009

Foster, L., A. Waagen, N. Aijaz, M. Hurley, A. Luis, J. Rinsky, C. Satyavolu, M.J. Way, P. Gazis, and A. Srivastava, 2009: Stable and efficient Gaussian process calculations. J. Mach. Learn. Res., 10, 857-882.

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.

  • Get PDF (241 kB)
  • PDF documents require the free Adobe Reader or compatible viewing software to be viewed.

Export citation: [ BibTeX ] [ RIS ]

BibTeX Citation

  author={Foster, L. and Waagen, A. and Aijaz, N. and Hurley, M. and Luis, A. and Rinsky, J. and Satyavolu, C. and Way, M. J. and Gazis, P. and Srivastava, A.},
  title={Stable and efficient Gaussian process calculations},
  journal={Journal of Machine Learning Research},

[ Close ]

RIS Citation

ID  - fo04000r
AU  - Foster, L.
AU  - Waagen, A.
AU  - Aijaz, N.
AU  - Hurley, M.
AU  - Luis, A.
AU  - Rinsky, J.
AU  - Satyavolu, C.
AU  - Way, M. J.
AU  - Gazis, P.
AU  - Srivastava, A.
PY  - 2009
TI  - Stable and efficient Gaussian process calculations
JA  - J. Mach. Learn. Res.
JO  - Journal of Machine Learning Research
VL  - 10
SP  - 857
EP  - 882
ER  -

[ Close ]

• Return to 2009 Publications

• Return to Publications Homepage