On the Neural Tangent Kernel of Equilibrium Models
ICLR 2023(2023)
Abstract
This work studies the neural tangent kernel (NTK) of deep equilibrium (DEQ) model, a practical ``infinite-depth'' architecture which directly computes the infinite-depth limit of a weight-tied network via root-finding. Even though the NTK of a fully-connected neural network is stochastic if its width and depth both tend to infinity simultaneously, we show that contrarily a DEQ model still enjoys a deterministic NTK despite its width and depth going to infinity at the same time. Moreover, such deterministic NTK can be found efficiently via root-finding.
MoreTranslated text
Key words
Equilibrium model,neural tangent kernel
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined