Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures
Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated
remarkable success on various tasks. There is, however, a lack of theoretical understanding …
remarkable success on various tasks. There is, however, a lack of theoretical understanding …
Robust Learning in Bayesian Parallel Branching Graph Neural Networks: The Narrow Width Limit
Z Zhang, H Sompolinsky - arXiv preprint arXiv:2407.18807, 2024 - arxiv.org
The infinite width limit of random neural networks is known to result in Neural Networks as
Gaussian Process (NNGP)(Lee et al.[2018]), characterized by task-independent kernels. It is …
Gaussian Process (NNGP)(Lee et al.[2018]), characterized by task-independent kernels. It is …