Login
- Title:
Maximum Likelihood Estimates for Gaussian Mixtures Are Transcendental
- Document type:
- Buchbeitrag
- Author(s):
- Améndola, Carlos; Drton, Mathias; Sturmfels, Bernd
- Pages contribution:
- 579-590
- Abstract:
- Gaussian mixture models are central to classical statistics, widely used in the information sciences, and have a rich mathematical structure. We examine their maximum likelihood estimates through the lens of algebraic statistics. The MLE is not an algebraic function of the data, so there is no notion of ML degree for these models. The critical points of the likelihood function are transcendental, and there is no bound on their number, even for mixtures of two univariate Gaussians.
- Keywords:
- Algebraic statistics, Expectation maximization, Maximum likelihood, Mixture model, Normal distribution, Transcendence theory
- Dewey Decimal Classification:
- 510 Mathematik
- Book title:
- Mathematical Aspects of Computer and Information Sciences
- Book subtitle:
- 6th International Conference, MACIS 2015, Berlin, Germany, November 11-13, 2015, Revised Selected Papers
- Publisher:
- Springer International Publishing
- Date of publication:
- 16.04.2016
- Year:
- 2016
- Quarter:
- 2. Quartal
- Year / month:
- 2016-04
- Month:
- Apr
- Pages:
- 579-590
- Print-ISBN:
- 97833193285849783319328591
- Language:
- en
- DOI:
- doi:10.1007/978-3-319-32859-1_49
BibTeX