Preprint
Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum
Abstract
We derive new bounds for the condition number of kernel matrices, which we
then use to enhance existing non-asymptotic test error bounds for kernel
Authors
Cheng TS; Lucchi A; Kratsios A; Belius D
Publication date
February 2, 2024
DOI
10.48550/arxiv.2402.01297
Preprint server
arXiv