Online gradient descent algorithms for functional data learning

DOI10.1016/j.jco.2021.101635OpenAlexW4200574550MaRDI QIDQ2121498

Jun Fan, Xiaming Chen, Bohao Tang, Xin Guo

Publication date: 4 April 2022

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2021.101635

zbMATH Keywords

learning theoryerror analysisonline learningreproducing kernel Hilbert spacegradient descent

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Related Items (4)

Capacity dependent analysis for functional online learning algorithms ⋮ High-probability generalization bounds for pointwise uniformly stable algorithms ⋮ Approximation of nonlinear functionals using deep ReLU networks ⋮ Online regularized learning algorithm for functional data

Uses Software

• fda (R)

Cites Work

• Unnamed Item
• A reproducing kernel Hilbert space approach to functional linear regression
• Prediction in functional linear regression
• On regularization algorithms in learning theory
• Methodology and convergence rates for functional linear regression
• Online gradient descent learning algorithms
• Fast and strong convergence of online learning algorithms
• Optimal rates for the regularized least-squares algorithm
• Functional data analysis.
• An RKHS approach to estimate individualized treatment rules based on functional predictors
• Error analysis on regularized regression based on the maximum correntropy criterion
• Sparse regularized learning in the reproducing kernel Banach spaces with the \(\ell^1\) norm
• Kernel regression, minimax rates and effective dimensionality: Beyond the regular case
• Learning Theory
• Support Vector Machines
• A new concentration result for regularized risk minimizers
• Any Discrimination Rule Can Have an Arbitrarily Bad Probability of Error for Finite Sample Size
• Minimax and Adaptive Prediction for Functional Linear Regression
• Distributed learning with indefinite kernels
• Shorter Notes: Some Operator Monotone Functions
• $A \geq B \geq 0$ Assures $(B^r A^p B^r)^{1/q} \geq B^{(p+2r)/q$ for $r \geq 0$, $p \geq 0$, $q \geq 1$ with $(1 + 2r)q \geq p + 2r$
• Optimal learning with Gaussians and correntropy loss

This page was built for publication: Online gradient descent algorithms for functional data learning