| HAL-Inria | Publications, software ... of Inria's scientists |
Journal articles
Intrinsic Dimension Estimation by Maximum Likelihood in Isotropic Probabilistic PCA
Abstract : A central issue in dimension reduction is choosing a sensible number of dimensions to be retained. This work demonstrates the surprising result of the asymptotic consistency of the maximum likelihood criterion for determining the intrinsic dimension of a dataset in an isotropic version of Probabilistic Principal Component Analysis (PPCA). Numerical experiments on simulated and real datasets show that the maximum likelihood criterion can actually be used in practice and outperforms existing intrinsic dimension selection criteria in various situations. This paper exhibits and outlines the limits of the maximum likelihood criterion. It leads to recommend the use of the AIC criterion in specific situations. A useful application of this work would be the automatic selection of intrinsic dimensions in mixtures of isotropic PPCA for classification.
Cited literature [33 references]
https://hal.archives-ouvertes.fr/hal-00440372
Contributor : Charles Bouveyron <>
Submitted on : Monday, July 11, 2011 - 9:35:22 AM
Last modification on : Tuesday, January 19, 2021 - 11:08:38 AM
Long-term archiving on: : Wednesday, October 12, 2011 - 2:21:13 AM
Contributor : Charles Bouveyron <>
Submitted on : Monday, July 11, 2011 - 9:35:22 AM
Last modification on : Tuesday, January 19, 2021 - 11:08:38 AM
Long-term archiving on: : Wednesday, October 12, 2011 - 2:21:13 AM
File
revision_PPCAds.pdf
Files produced by the author(s)