The content delves into the cost of overfitting in noisy kernel ridge regression, taking an agnostic view. It explores benign, tempered, and catastrophic overfitting scenarios under a Gaussian universality ansatz. The analysis provides a refined characterization of these types of overfitting based on the sample size and effective ranks of the covariance matrix. The paper also discusses inner-product kernels in the polynomial regime and their implications for generalization performance.
A otro idioma
del contenido fuente
arxiv.org
Ideas clave extraídas de
by Lijia Zhou,J... a las arxiv.org 03-25-2024
https://arxiv.org/pdf/2306.13185.pdfConsultas más profundas