DeepAI AI Chat
Log In Sign Up

Neural Tangent Kernel: A Survey

by   Eugene Golikov, et al.

A seminal work [Jacot et al., 2018] demonstrated that training a neural network under specific parameterization is equivalent to performing a particular kernel method as width goes to infinity. This equivalence opened a promising direction for applying the results of the rich literature on kernel methods to neural nets which were much harder to tackle. The present survey covers key results on kernel convergence as width goes to infinity, finite-width corrections, applications, and a discussion of the limitations of the corresponding method.


page 25

page 26


On the infinite width limit of neural networks with a standard parameterization

There are currently two parameterizations used to derive fixed kernels c...

Neural tangent kernel analysis of shallow α-Stable ReLU neural networks

There is a recent literature on large-width properties of Gaussian neura...

Neural Tangent Kernel Beyond the Infinite-Width Limit: Effects of Depth and Initialization

Neural Tangent Kernel (NTK) is widely used to analyze overparametrized n...

On Exact Computation with an Infinitely Wide Neural Net

How well does a classic deep net architecture like AlexNet or VGG19 clas...

WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points

Generative adversarial networks (GAN) are a widely used class of deep ge...

Tensor Programs II: Neural Tangent Kernel for Any Architecture

We prove that a randomly initialized neural network of *any architecture...