A reproducing kernel Hilbert space approach to functional linear regression

Abstract

We study in this paper a smoothness regularization method for functional linear regression and provide a unified treatment for both the prediction and estimation problems. By developing a tool on simultaneous diagonalization of two positive definite kernels, we obtain shaper results on the minimax rates of convergence and show that smoothness regularized estimators achieve the optimal rates of convergence for both prediction and estimation under conditions weaker than those for the functional principal components based methods developed in the literature. Despite the generality of the method of regularization, we show that the procedure is easily implementable. Numerical results are obtained to illustrate the merits of the method and to demonstrate the theoretical developments.

Published in at http://dx.doi.org/10.1214/09-AOS772 the Annals of Statistics (http://www.imstat.org/aos/) by the Institute of Mathematical Statistics (http://www.imstat.org)

References in corpus (6)

• Functional linear regression analysis for longitudinal data
• Generalized functional linear models
• Prediction in functional linear regression
• Methodology and convergence rates for functional linear regression
• Smoothing splines estimators for functional linear regression
• Nonparametric estimation in functional linear models with second order stationary regressors

Cited by in corpus (47)

• Estimation in functional linear quantile regression
• Predicting Clinical Outcomes in Glioblastoma: An Application of Topological and Functional Data Analysis
• A Smooth and Locally Sparse Estimator for Functional Linear Regression via Functional SCAD Penalty
• Nonparametric inference in generalized functional linear models
• Optimal Penalized Function-on-Function Regression under a Reproducing Kernel Hilbert Space Framework
• Intrinsic Riemannian Functional Data Analysis
• Robust functional regression based on principal components
• Low-Rank Covariance Function Estimation for Multidimensional Functional Data
• Conditional Independence Testing in Hilbert Spaces with Applications to Functional Data Analysis
• On regularized polynomial functional regression
• Functional Linear Regression with Mixed Predictors
• Regression with genuinely functional errors-in-covariates
• Intrinsic Wasserstein Correlation Analysis
• PCA-based estimation for functional linear regression with functional responses
• Functional Autoregressive Processes in Reproducing Kernel Hilbert Spaces
• Physics-Information-Aided Kriging: Constructing Covariance Functions using Stochastic Simulation Models
• A simple method to construct confidence bands in functional linear regression
• Shrinkage Estimation and Selection for Multiple Functional Regression
• Minimax Optimal Rates of Estimation in Functional ANOVA Models with Derivatives
• Learning Partial Differential Equations in Reproducing Kernel Hilbert Spaces
• Nonparametric Operator-Regularized Covariance Function Estimation for Functional Data
• The interplay between system identification and machine learning
• A note on estimation in Hilbertian linear models
• Optimal Prediction in an Additive Functional Model
• A divergence formula for regularization methods with an L2 constraint
• Truncated Linear Models for Functional Data
• Profile Estimation for Partial Functional Partially Linear Single-Index Model
• Optimal Global Test for Functional Regression
• Reproducing kernels based schemes for nonparametric regression
• High-Dimensional Spatial Quantile Function-on-Scalar Regression
• Kernel-based estimation for partially functional linear model: Minimax rates and randomized sketches
• A Bayesian approach to functional regression: theory and computation
• Interpretable discriminant analysis for functional data supported on random nonlinear domains with an application to Alzheimer's disease
• Estimating Historical Functional Linear Models with a Nested Group Bridge Approach
• Wasserstein Regression
• Sparse logistic regression on functional data
• Bayesian Classification of Multiclass Functional Data
• Optimal prediction for kernel-based semi-functional linear regression
• A reproducing kernel Hilbert space framework for functional data classification
• Federated Classification using Parsimonious Functions in Reproducing Kernel Hilbert Spaces
• Estimating Functional Linear Mixed-Effects Regression Models
• Operator Reproducing Kernel Hilbert Spaces
• Nonparametric principal subspace regression
• Empirical likelihood inference for partial functional linear regression models based on B spline
• $L_1$-Penalization in Functional Linear Regression with Subgaussian Design
• Hybrid Regularisation of Functional Linear Models
• Minimax Prediction for Functional Linear Regression with Functional Responses in Reproducing Kernel Hilbert Spaces