Previous work has shown that DNNs with large depth L and
L_2-regularizat...
The L_2-regularized loss of Deep Linear Networks (DLNs) with more than
o...
We show that the representation cost of fully connected neural networks ...
We study the loss surface of DNNs with L_2 regularization. We show that
...
Spectral analysis is a powerful tool, decomposing any function into simp...
For deep linear networks (DLN), various hyperparameters alter the dynami...
We study the SIMP method with a density field generated by a fully-conne...
We study how permutation symmetries in overparameterized multi-layer neu...
We study the risk (i.e. generalization error) of Kernel Ridge Regression...
Random Feature (RF) models are used as efficient parametric approximatio...
The dynamics of DNNs during gradient descent is described by the so-call...
In this paper, we analyze a number of architectural features of Deep Neu...
Two distinct limits for deep learning as the net width h→∞ have been
pro...
We provide a description for the evolution of the generalization perform...
At initialization, artificial neural networks (ANNs) are equivalent to
G...