The effectiveness of implicit neural networks in different tasks has been proven. However, there is a need for theoretical analysis to understand the connections and distinctions between implicit and explicit networks. This study focuses on high-dimensional implicit neural networks and presents the equivalent high-dimensional versions of conjugate kernels and neural tangent kernels. Based on this, we establish the equivalence between implicit and explicit networks in high dimensions.
A High-dimensional Perspective on the Equivalence of Implicit and Explicit Neural Networks (arXiv:2308.16425v1 [cs.LG])
