Pre-trained machine learning (ML) models have shown great performance fo...
Training large neural network (NN) models requires extensive memory
reso...
Physics modeling is critical for modern science and engineering applicat...
To address the communication bottleneck problem in distributed optimizat...
The standard normalization method for neural network (NN) models used in...
We present PyHessian, a new scalable framework that enables fast computa...
It has been observed that residual networks can be viewed as the explici...
Deep Neural Networks are quite vulnerable to adversarial perturbations.
...
Optimal parameter initialization remains a crucial problem for neural ne...
Stochastic Gradient Descent (SGD) methods using randomly selected batche...
We consider statistical and algorithmic aspects of solving large-scale
l...
We consider the problem of improving the efficiency of randomized Fourie...
We consider statistical as well as algorithmic aspects of solving large-...