Despite the success of equivariant neural networks in scientific
applica...
In mathematical optimization, second-order Newton's methods generally
co...
Existing gradient-based optimization methods update the parameters local...
Existing equivariant neural networks for continuous groups require
discr...
Generation and transformation of images and videos using artificial
inte...
Locating the source of an epidemic, or patient zero (P0), can provide
cr...
To deepen our understanding of graph neural networks, we investigate the...
We show that in a deep neural network trained with ReLU, the low-lying l...