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

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Worst-Case Bounds for Gaussian Process Models

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

Seeger,  M
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

Kakade, S., Seeger, M., & Foster, D. (2006). Worst-Case Bounds for Gaussian Process Models. Advances in Neural Information Processing Systems 18: Proceedings of the 2005 Conference, 619-626.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-D1F3-B
Abstract
We present a competitive analysis of some non-parametric Bayesian algorithms in a worst-case online learning setting, where no probabilistic assumptions about the generation of the data are made. We consider models which use a Gaussian process prior (over the space of all functions) and provide bounds on the regret (under the log loss) for commonly used non-parametric Bayesian algorithms - including Gaussian regression and logistic regression - which show how these algorithms can perform favorably under rather general conditions. These bounds explicitly handle the infinite dimensionality of these non-parametric classes in a natural way. We also make formal connections to the minimax and emphminimum description length (MDL) framework. Here, we show precisely how Bayesian Gaussian regression is a minimax strategy.