Neural Tangent Kernel: A Survey
It provides a comprehensive overview for researchers in machine learning, but is incremental as it synthesizes existing work without new findings.
This survey reviews the Neural Tangent Kernel (NTK) theory, which shows that training wide neural networks under specific conditions is equivalent to kernel methods, enabling the application of kernel literature to neural networks.
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.