Penalized empirical relaxed greedy algorithm for fixed design Gaussian regression

DOI10.1142/S0219691316500193MaRDI QIDQ2818315zbMATH OpenFDO

Authors Chen Chen, Na Chen

Publication date 7 September 2016

Published in International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1142/S0219691316500193

zbMATH Keywords

fixed design Gaussian regressiongreedy algorithmoracle inequalitypenalized empirical risk

Mathematics Subject Classification ID

Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Multidimensional problems (41A63) Density estimation (62G07)

Recommendations

• Approximation and learning by greedy algorithms
• Optimality of the rescaled pure greedy learning algorithms
• On the convergence rate of kernel-based sequential greedy regression
• Learning rates of multi-kernel regression by orthogonal greedy algorithm
• Relaxation in greedy approximation

Cites work

• Approximation and learning by greedy algorithms
• Greedy approximation
• Linear functional regression: The case of fixed design and functional response

Cited in

(2)

• Variant of Greedy Randomized Gauss-Seidel Method for Ridge Regression
• Optimality of the rescaled pure greedy learning algorithms

This page was built for publication: Penalized empirical relaxed greedy algorithm for fixed design Gaussian regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2818315)