Conditioning of random Fourier feature matrices: double descent and generalization error

DOI10.1093/IMAIAI/IAAD054MaRDI QIDQ6638517zbMATH OpenFDO

Authors Zhijun Chen, Hayden Schaeffer

Publication date 14 November 2024

Published in Information and Inference: A Journal of the IMA (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1093/IMAIAI/IAAD054

zbMATH Keywords

conditioningdouble descentrandom feature modelsrestricted isometry property

Mathematics Subject Classification ID

Statistics (62-XX)

Recommendations

• A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
• The Generalization Error of Random Features Regression: Precise Asymptotics and the Double Descent Curve
• Towards a unified analysis of random Fourier features
• Two models of double descent for weak features
• A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics

Cited in

(3)

• A random matrix analysis of random Fourier features: beyond the Gaussian kernel, a precise phase transition, and the corresponding double descent*
• Solving partial differential equations with random feature models
• On the approximation of Koopman eigenfunctions using random features

This page was built for publication: Conditioning of random Fourier feature matrices: double descent and generalization error

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6638517)