The asymptotic spectrum of the Hessian of DNN throughout training
Franck Gabriel ⋅ Arthur Jacot ⋅ Clement Hongler
Abstract
The dynamics of DNNs during gradient descent is described by the so-called Neural Tangent Kernel (NTK). In this article, we show that the NTK allows one to gain precise insight into the Hessian of the cost of DNNs: we obtain a full characterization of the asymptotics of the spectrum of the Hessian, at initialization and during training.
Chat is not available.
Successful Page Load