Search Results for author:
Found 7 papers, 4 papers with code
Dynamic Sparse Training with Structured Sparsity
Dynamic Sparse Training (DST) methods achieve state-of-the-art results in sparse neural network training, matching the generalization of dense models while enabling sparse training and inference.
Bounding generalization error with input compression: An empirical study with infinite-width networks
Estimating the Generalization Error (GE) of Deep Neural Networks (DNNs) is an important task that often relies on availability of held-out data.
Are wider nets better given the same number of parameters?
Empirical studies demonstrate that the performance of neural networks improves with increasing number of parameters.
Batch Normalization is a Cause of Adversarial Vulnerability
Batch normalization (batch norm) is often used in an attempt to stabilize and accelerate training in deep neural networks.
QuCumber: wavefunction reconstruction with neural networks
As we enter a new era of quantum technology, it is increasingly important to develop methods to aid in the accurate preparation of quantum states for a variety of materials, matter, and devices.
Quantum Physics Strongly Correlated Electrons
Adversarial Examples as an Input-Fault Tolerance Problem
We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input.
A Rate-Distortion Theory of Adversarial Examples
The generalization ability of deep neural networks (DNNs) is intertwined with model complexity, robustness, and capacity.
