Optimal Rates for Functional Linear Regression with General Regularization

2024/06/14 by Naveen Gupta, Gupta, Naveen, Bharath K. Sriperumbudur +2 · 1 citation
Engineering · #Control Systems and Identification

paper · pdf · doi:10.48550/arxiv.2406.10005

Abstract

Functional linear regression is one of the fundamental and well-studied methods in functional data analysis. In this work, we investigate the functional linear regression model within the context of reproducing kernel Hilbert space by employing general spectral regularization to approximate the slope function with certain smoothness assumptions. We establish optimal convergence rates for estimation and prediction errors associated with the proposed method under a Hölder type source condition, which generalizes and sharpens all the known results in the literature.

Cited by

• Convergence Analysis of function-on-function Polynomial regression model

Related

• Statistical Optimality of Divide and Conquer Kernel-based Functional Linear Regression
• Convergence Analysis of Kernel Conjugate Gradient for Functional Linear Regression
• Minimax Prediction for Functional Linear Regression with Functional Responses in Reproducing Kernel Hilbert Spaces
• Optimal prediction for kernel-based semi-functional linear regression
• Online Regularized Learning Algorithm for Functional Data