Sampled forms of functional PCA in reproducing kernel Hilbert spaces

by   Arash A. Amini, et al.

We consider the sampling problem for functional PCA (fPCA), where the simplest example is the case of taking time samples of the underlying functional components. More generally, we model the sampling operation as a continuous linear map from H to R^m, where the functional components to lie in some Hilbert subspace H of L^2, such as a reproducing kernel Hilbert space of smooth functions. This model includes time and frequency sampling as special cases. In contrast to classical approach in fPCA in which access to entire functions is assumed, having a limited number m of functional samples places limitations on the performance of statistical procedures. We study these effects by analyzing the rate of convergence of an M-estimator for the subspace spanned by the leading components in a multi-spiked covariance model. The estimator takes the form of regularized PCA, and hence is computationally attractive. We analyze the behavior of this estimator within a nonasymptotic framework, and provide bounds that hold with high probability as a function of the number of statistical samples n and the number of functional samples m. We also derive lower bounds showing that the rates obtained are minimax optimal.


page 1

page 2

page 3

page 4


Uniform Function Estimators in Reproducing Kernel Hilbert Spaces

This paper addresses the problem of regression to reconstruct functions,...

On the Improved Rates of Convergence for Matérn-type Kernel Ridge Regression, with Application to Calibration of Computer Models

Kernel ridge regression is an important nonparametric method for estimat...

Spectral Density Estimation of Function-Valued Spatial Processes

The spectral density function describes the second-order properties of a...

Optimal Sampling Points in Reproducing Kernel Hilbert Spaces

The recent developments of basis pursuit and compressed sensing seek to ...

Unified RKHS Methodology and Analysis for Functional Linear and Single-Index Models

Functional linear and single-index models are core regression methods in...

Discussion contribution "Functional models for time-varying random objects” by Dubey and Müller (to appear in JRSS-B)

In an inspiring paper Dubey and Müller (DM) extend PCA to the case that ...

Experimental Design for Linear Functionals in Reproducing Kernel Hilbert Spaces

Optimal experimental design seeks to determine the most informative allo...

Please sign up or login with your details

Forgot password? Click here to reset