Error analysis of the moving least-squares regression learning algorithm with β-mixing and non-identical sampling

DOI10.1080/00207160.2019.1636231OpenAlexW2954026080MaRDI QIDQ5030625

Qin Guo, Pei Xin Ye

Publication date: 17 February 2022

Published in: International Journal of Computer Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00207160.2019.1636231

zbMATH Keywords

weight functionlearning ratemixing sequencenon-identical samplingmoving least-squares methodtotal error

Mathematics Subject Classification ID

Computational learning theory (68Q32) General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Uses Software

• KernSmooth

Cites Work

• Unnamed Item
• Unregularized online learning algorithms with general loss functions
• On the possibilistic approach to linear regression models involving uncertain, indeterminate or interval data
• Classification with non-i.i.d. sampling
• Toward approximate moving least squares approximation with irregularly spaced centers
• Concentration estimates for the moving least-square method in learning theory
• Statistical analysis of the moving least-squares method with unbounded sampling
• Hermite type moving-least-squares approximations
• Learning from dependent observations
• Moving least-square method in learning theory
• Basic properties of strong mixing conditions. A survey and some open questions
• Least-square regularized regression with non-iid sampling
• Learning performance of regularized moving least square regression
• Learning rates of least-square regularized regression
• Coefficient-based regularized regression with dependent and unbounded sampling
• Coefficient regularized regression with non-iid sampling
• Learning Theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• Deep distributed convolutional neural networks: Universality
• Error analysis of the moving least-squares method with non-identical sampling

This page was built for publication: Error analysis of the moving least-squares regression learning algorithm with β-mixing and non-identical sampling