Header logo is ei

Occam's Razor


Conference Paper


The Bayesian paradigm apparently only sometimes gives rise to Occam's Razor; at other times very large models perform well. We give simple examples of both kinds of behaviour. The two views are reconciled when measuring complexity of functions, rather than of the machinery used to implement them. We analyze the complexity of functions for some linear in the parameter models that are equivalent to Gaussian Processes, and always find Occam's Razor at work.

Author(s): Rasmussen, CE. and Ghahramani, Z.
Book Title: Advances in Neural Information Processing Systems 13
Journal: Advances in Neural Information Processing Systems 13
Pages: 294-300
Year: 2001
Month: April
Day: 0
Editors: Leen, T.K. , T.G. Dietterich, V. Tresp
Publisher: MIT Press

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: Fourteenth Annual Neural Information Processing Systems Conference (NIPS 2000)
Event Place: Denver, CO, USA

Address: Cambridge, MA, USA
Digital: 0
ISBN: 0-262-12241-3
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF


  title = {Occam's Razor},
  author = {Rasmussen, CE. and Ghahramani, Z.},
  journal = {Advances in Neural Information Processing Systems 13},
  booktitle = {Advances in Neural Information Processing Systems 13},
  pages = {294-300},
  editors = {Leen, T.K. , T.G. Dietterich, V. Tresp},
  publisher = {MIT Press},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  address = {Cambridge, MA, USA},
  month = apr,
  year = {2001},
  month_numeric = {4}