Large-scale non-convex optimization problems are expensive to solve due ...
Most state-of-the-art Graph Neural Networks (GNNs) can be defined as a f...
The current success of deep learning depends on large-scale labeled data...
We study how neural networks trained by gradient descent extrapolate, i....
Deep neural networks generalize well on unseen data though the number of...
Neural networks have successfully been applied to solving reasoning task...
Modern neural networks can have tens of millions of parameters, and are ...