de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Information Consistency of Nonparametric Gaussian Process Methods

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84205

Seeger,  MW
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Seeger, M., Kakade, S., & Foster, D. (2008). Information Consistency of Nonparametric Gaussian Process Methods. IEEE Transactions on Information Theory, 54(5), 2376-2382. doi:10.1109/TIT.2007.915707.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-C963-E
Abstract
Abstract—Bayesian nonparametric models are widely and successfully used for statistical prediction. While posterior consistency properties are well studied in quite general settings, results have been proved using abstract concepts such as metric entropy, and they come with subtle conditions which are hard to validate and not intuitive when applied to concrete models. Furthermore, convergence rates are difficult to obtain. By focussing on the concept of information consistency for Bayesian Gaussian process (GP)models, consistency results and convergence rates are obtained via a regret bound on cumulative log loss. These results depend strongly on the covariance function of the prior process, thereby giving a novel interpretation to penalization with reproducing kernel Hilbert space norms and to commonly used covariance function classes and their parameters. The proof of the main result employs elementary convexity arguments only. A theorem of Widom is used in order to obtain precise convergence rates for several covariance functions widely used in practice.