Generalization in kernel regression under realistic assumptions
D Barzilai, O Shamir - arXiv preprint arXiv:2312.15995, 2023 - arxiv.org
It is by now well-established that modern over-parameterized models seem to elude the bias-
variance tradeoff and generalize well despite overfitting noise. Many recent works attempt to …
variance tradeoff and generalize well despite overfitting noise. Many recent works attempt to …
Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
The success of over-parameterized neural networks trained to near-zero training error has
caused great interest in the phenomenon of benign overfitting, where estimators are …
caused great interest in the phenomenon of benign overfitting, where estimators are …
Phase transition in noisy high-dimensional random geometric graphs
We study the problem of detecting latent geometric structure in random graphs. To this end,
we consider the soft high-dimensional random geometric graph G (n, p, d, q), where each of …
we consider the soft high-dimensional random geometric graph G (n, p, d, q), where each of …
Learning curves for Gaussian process regression with power-law priors and targets
We characterize the power-law asymptotics of learning curves for Gaussian process
regression (GPR) under the assumption that the eigenspectrum of the prior and the …
regression (GPR) under the assumption that the eigenspectrum of the prior and the …
Why shallow networks struggle with approximating and learning high frequency: A numerical study
In this work, a comprehensive numerical study involving analysis and experiments shows
why a two-layer neural network has difficulties handling high frequencies in approximation …
why a two-layer neural network has difficulties handling high frequencies in approximation …
Entrywise error bounds for low-rank approximations of kernel matrices
A Modell - arXiv preprint arXiv:2405.14494, 2024 - arxiv.org
In this paper, we derive entrywise error bounds for low-rank approximations of kernel
matrices obtained using the truncated eigen-decomposition (or singular value …
matrices obtained using the truncated eigen-decomposition (or singular value …
[图书][B] Generalization of Wide Neural Networks from the Perspective of Linearization and Kernel Learning
H Jin - 2022 - search.proquest.com
Recently people showed that wide neural networks can be approximated by linear models
under gradient descent [JGH18a, LXS19a]. In this dissertation we study generalization of …
under gradient descent [JGH18a, LXS19a]. In this dissertation we study generalization of …