Neural tangent kernel analysis of shallow $\alpha$-Stable ReLU neural networks. (arXiv:2206.08065v1 [cs.LG])

Web: http://arxiv.org/abs/2206.08065

There is a recent literature on large-width properties of Gaussian neural
networks (NNs), i.e. NNs whose weights are distributed according to Gaussian
distributions. Two popular problems are: i) the study of the large-width
behaviour of NNs, which provided a characterization of the infinitely wide
limit of a rescaled NN in terms of a Gaussian process; ii) the study of the
large-width training dynamics of NNs, which set forth an equivalence between
training the rescaled NN and performing a kernel regression …

analysis arxiv kernel lg networks neural neural networks relu