Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data

“Handbook of Mathematical Functions.”

J.. Florentin, Milton Abramowitz and Irene. Stegun · 1966

Earlier work this paper cites.

“Spin glass theory and beyond: An Introduction to the Replica Method and Its Applications”

Marc Mezard, Giorgio Parisi and Miguel Virasoro · 1987

Earlier work this paper cites.

“Modified Airy Function and WKB Solutions to the Wave Equation”

A.K.Ghatak · 1991

Earlier work this paper cites.

“Computing a family of reproducing kernels for statistical applications”

Christine Thomas-Agnan · 1996

Earlier work this paper cites.

“Learning with Kernels”

A.J. Smola and B. Scholkopf · 2002

Earlier work this paper cites.

“Ordinary differential equations and Dynamical Systems”

Gerald Teschl · 2004

Earlier work this paper cites.

“Numerical Approximation of Highly Oscillatory Integrals”

S. Olver · 2008

Earlier work this paper cites.

“Visualizing data using t-SNE.”

Laurens Van and Geoffrey Hinton · 2008

Cited alongside, same era.

“Deep learning scaling is predictable, empirically”

J. Hestness et al · 2017

Cited alongside, same era.

“Neural tangent kernel: Convergence and generalization in neural networks”

Arthur Jacot, Franck Gabriel and Clément Hongler · 2018

Cited alongside, same era.

“Introduction to RKHS, and some simple kernel algorithms”

Gretton · 2019

Cited alongside, same era.

“Frequency bias in neural networks for input of non-uniform density”

Ronen Basri et al · 2020

Cited alongside, same era.

“Spectrum dependent learning curves in kernel regression andwide neural networks”

Blake Bordelon, Abdulkadir Canatar and Cengiz Pehlevan · 2020

Cited alongside, same era.

“Kernel alignment risk estimator: Risk prediction from training data”

Arthur Jacot et al · 2020

Later among the works it cites.

“Asymptotic learning curves of kernel methods: Empirical data versus teacher-student paradigm”

Stefano Spigler, Mario Geiger and Matthieu Wyart · 2020

Later among the works it cites.

“Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks”

Abdulkadir Canatar, Blake Bordelon and Cengiz Pehlevan · 2021

Later among the works it cites.

“Generalization Error Rates in Kernel Regression: The Crossover from the Noiseless to Noisy Regime”

H. Cui et al · 2021

Later among the works it cites.

“Capturing the learning curves of generic features maps for realistic data sets with a teacher-student model”

B. Loureiro et al · 2021

Later among the works it cites.