Empirical Inference

Infinite dimensional exponential families by reproducing kernel Hilbert spaces

2005

Conference Paper

ei


The purpose of this paper is to propose a method of constructing exponential families of Hilbert manifold, on which estimation theory can be built. Although there have been works on infinite dimensional exponential families of Banach manifolds (Pistone and Sempi, 1995; Gibilisco and Pistone, 1998; Pistone and Rogantin, 1999), they are not appropriate to discuss statistical estimation with finite number of samples; the likelihood function with finite samples is not continuous on the manifold. In this paper we use a reproducing kernel Hilbert space as a functional space for constructing an exponential manifold. A reproducing kernel Hilbert space is dened as a Hilbert space of functions such that evaluation of a function at an arbitrary point is a continuous functional on the Hilbert space. Since we can discuss the value of a function with this space, it is very natural to use a manifold associated with a reproducing kernel Hilbert space as a basis of estimation theory. We focus on the maximum likelihood estimation (MLE) with the exponential manifold of a reproducing kernel Hilbert space. As in many non-parametric estimation methods, straightforward extension of MLE to an infinite dimensional exponential manifold suffers the problem of ill-posedness caused by the fact that the estimator should be chosen from the infinite dimensional space with only finite number of constraints given by the data. To solve this problem, a pseudo-maximum likelihood method is proposed by restricting the infinite dimensional manifold to a series of finite dimensional submanifolds, which enlarge as the number of samples increases. Some asymptotic results in the limit of infinite samples are shown, including the consistency of the pseudo-MLE.

Author(s): Fukumizu, K.
Book Title: IGAIA 2005
Journal: Proceedings of the 2nd International Symposium on Information Geometry and its Applications (IGAIA 2005)
Pages: 324-333
Year: 2005
Month: December
Day: 0

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

Event Name: 2nd International Symposium on Information Geometry and its Applications
Event Place: Tokyo, Japan

Digital: 0
Language: en
Organization: Max-Planck-Gesellschaft
School: Biologische Kybernetik

Links: PDF
Web

BibTex

@inproceedings{5589,
  title = {Infinite dimensional exponential families by reproducing kernel Hilbert spaces},
  author = {Fukumizu, K.},
  journal = {Proceedings of the 2nd International Symposium on Information Geometry and its Applications (IGAIA 2005)},
  booktitle = {IGAIA 2005},
  pages = {324-333},
  organization = {Max-Planck-Gesellschaft},
  school = {Biologische Kybernetik},
  month = dec,
  year = {2005},
  doi = {},
  month_numeric = {12}
}