Upper and lower bounds on the learning curve for Gaussian processes

Christopher K. I. Williams, Francesco Vivarelli

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper we introduce and illustrate non-trivial upper and lower bounds on the learning curves for one-dimensional Gaussian Processes. The analysis is carried out emphasising the effects induced on the bounds by the smoothness of the random process described by the Modified Bessel and the Squared Exponential covariance functions. We present an explanation of the early, linearly-decreasing behavior of the learning curves and the bounds as well as a study of the asymptotic behavior of the curves. The effects of the noise level and the lengthscale on the tightness of the bounds are also discussed.

Original languageEnglish
Pages (from-to)77-102
Number of pages26
JournalMachine Learning
Volume40
Issue number1
DOIs
Publication statusPublished - Jul 2000

Keywords

  • non-trivial
  • Gaussian Processes
  • modified Bessel
  • covariance functions
  • learning curves

Fingerprint

Dive into the research topics of 'Upper and lower bounds on the learning curve for Gaussian processes'. Together they form a unique fingerprint.

Cite this