Scaled Torus Principal Component Analysis

DOI10.1080/10618600.2022.2119985MaRDI QIDQ6180732zbMATH OpenFDO

Authors Eduardo García-Portugués, J. S. Marron

Publication date 22 January 2024

Published in Journal of Computational and Graphical Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2110.04758

zbMATH Keywords

dimension reductionprincipal component analysismultidimensional scalingdirectional statisticsstatistics on manifolds

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: A particularly challenging context for dimensionality reduction is multivariate circular data, i.e., data supported on a torus. Such kind of data appears, e.g., in the analysis of various phenomena in ecology and astronomy, as well as in molecular structures. This paper introduces Scaled Torus Principal Component Analysis (ST-PCA), a novel approach to perform dimensionality reduction with toroidal data. ST-PCA finds a data-driven map from a torus to a sphere of the same dimension and a certain radius. The map is constructed with multidimensional scaling to minimize the discrepancy between pairwise geodesic distances in both spaces. ST-PCA then resorts to principal nested spheres to obtain a nested sequence of subspheres that best fits the data, which can afterwards be inverted back to the torus. Numerical experiments illustrate how ST-PCA can be used to achieve meaningful dimensionality reduction on low-dimensional torii, particularly with the purpose of clusters separation, while two data applications in astronomy (three-dimensional torus) and molecular biology (on a seven-dimensional torus) show that ST-PCA outperforms existing methods for the investigated datasets.

Cites work

• scientific article; zbMATH DE number 5668397 (Why is no real title available?)
• scientific article; zbMATH DE number 5286897 (Why is no real title available?)
• scientific article; zbMATH DE number 3734973 (Why is no real title available?)
• scientific article; zbMATH DE number 847282 (Why is no real title available?)
• scientific article; zbMATH DE number 918093 (Why is no real title available?)
• A model and algorithm for multidimensional scaling with external constraints on the distances
• Analysis of principal nested spheres
• Backward nested descriptors asymptotics with inference on stem cell differentiation
• Backwards principal component analysis and principal nested relations
• Barycentric subspace analysis on manifolds
• Constrained best Euclidean distance embedding on a sphere: a matrix optimization approach
• Dihedral angles principal geodesic analysis using nonlinear statistics
• Embedding metric spaces in Euclidean space
• Functional relations in multidimensional scaling
• Modern multidimensional scaling. Theory and applications.
• Object shape representation via skeletal models (s-reps) and statistical analysis
• On optimal tests for rotational symmetry against new classes of hyperspherical distributions
• Overview of object oriented data analysis
• Principal arc analysis on direct product manifolds
• Principal component analysis for Riemannian manifolds, with an application to triangular shape spaces
• Recent advances in directional statistics
• Scale Space and PDE Methods in Computer Vision
• The Dissimilarity Representation for Pattern Recognition
• The Intrinsic Distribution and Selection Bias of Long-Period Cometary Orbits
• Torus principal component analysis with applications to RNA structure

This page was built for publication: Scaled Torus Principal Component Analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6180732)