OREGON STATE UNIVERSITY

You are here

Information-Geometric Dimensionality Reduction

TitleInformation-Geometric Dimensionality Reduction
Publication TypeJournal Article
Year of Publication2011
AuthorsCarter, K. M., R. Raich, W. G. Finn, and A. O. Hero, III
JournalIEEE Signal Processing Magazine
Volume28
Issue2
Pagination89 - 99
Date Published03/2011
ISSN1053-5888
Abstract

We consider the problem of dimensionality reduction and manifold learning when the domain of interest is a set of probability distributions instead of a set of Euclidean data vectors. In this problem, one seeks to discover a low dimensional representation, called embedding, that preserves certain properties such as distance between measured distributions or separation between classes of distributions. This article presents the methods that are specifically designed for low-dimensional embedding of information-geometric data, and we illustrate these methods for visualization in flow cytometry and demography analysis.

DOI10.1109/MSP.2010.939536
Short TitleIEEE Signal Process. Mag.