Spline estimation of functional principal components via manifold conjugate gradient algorithm

DOI10.1007/S11222-022-10175-2zbMATH Open1499.62020OpenAlexW4308749841MaRDI QIDQ2103990FDOQ2103990

Authors Shiyuan He, Hanxuan Ye, Kejun He 

Publication date 9 December 2022

Published in Statistics and Computing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2211.04784

zbMATH Keywords

functional data analysisStiefel manifoldpositive definite coneproduct manifoldmatrix Bregman divergence

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Factor analysis and principal components; correspondence analysis (62H25) Functional data analysis (62R10) Statistics on manifolds (62R30)

Abstract: Functional principal component analysis has become the most important dimension reduction technique in functional data analysis. Based on B-spline approximation, functional principal components (FPCs) can be efficiently estimated by the expectation-maximization (EM) and the geometric restricted maximum likelihood (REML) algorithms under the strong assumption of Gaussianity on the principal component scores and observational errors. When computing the solution, the EM algorithm does not exploit the underlying geometric manifold structure, while the performance of REML is known to be unstable. In this article, we propose a conjugate gradient algorithm over the product manifold to estimate FPCs. This algorithm exploits the manifold geometry structure of the overall parameter space, thus improving its search efficiency and estimation accuracy. In addition, a distribution-free interpretation of the loss function is provided from the viewpoint of matrix Bregman divergence, which explains why the proposed method works well under general distribution settings. We also show that a roughness penalization can be easily incorporated into our algorithm with a potentially better fit. The appealing numerical performance of the proposed method is demonstrated by simulation studies and the analysis of a Type Ia supernova light curve dataset.

Recommendations

• Functional principal components analysis via penalized rank one approximation
• Parametric Functional Principal Component Analysis
• Principal components analysis of sampled functions
• Bayesian estimation of principal components for functional data
• Penalized PCA approaches for B-spline expansions of smooth functional data

Cites work

• scientific article; zbMATH DE number 1818892 (Why is no real title available?)
• scientific article; zbMATH DE number 469124 (Why is no real title available?)
• scientific article; zbMATH DE number 469335 (Why is no real title available?)
• scientific article; zbMATH DE number 5223994 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• scientific article; zbMATH DE number 3047100 (Why is no real title available?)
• scientific article; zbMATH DE number 3105589 (Why is no real title available?)
• A brief introduction to manifold optimization
• A statistical perspective on ill-posed inverse problems (with discussion)
• Applied functional data analysis. Methods and case studies
• Asymptotic properties of penalized spline estimators in concave extended linear models: rates of convergence
• Clustering for Sparsely Sampled Functional Data
• Conic geometric optimization on the manifold of positive definite matrices
• Consistency of restricted maximum likelihood estimators of principal components
• Covariance, subspace, and intrinsic Crame/spl acute/r-Rao bounds
• Fast Computation of Fully Automated Log-Density and Log-Hazard Estimators
• From sparse to dense functional data and beyond
• Function minimization by conjugate gradients
• Functional Clustering and Identifying Substructures of Longitudinal Data
• Functional Data Analysis for Sparse Longitudinal Data
• Functional data analysis.
• Functional linear discriminant analysis for irregularly sampled curves
• Functional linear regression analysis for longitudinal data
• Matrix Nearness Problems with Bregman Divergences
• On the joint convexity of the Bregman divergence of matrices
• Optimization methods on Riemannian manifolds and their application to shape space
• Principal component models for sparse functional data
• Properties of principal component methods for functional and longitudinal data analysis
• Smoothed functional principal components analysis by choice of norm
• The Geometry of Algorithms with Orthogonality Constraints
• Uniform convergence rates for nonparametric regression and principal component analysis in functional/longitudinal data

Cited in

(1)

• Penalized spline estimation of principal components for sparse functional data: rates of convergence

Describes a project that uses

Uses Software

• fda (R)
• fpca

This page was built for publication: Spline estimation of functional principal components via manifold conjugate gradient algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2103990)