118 citations · 1.4k across the 52 of their papers we have counts for
11 papers · 1 filter
Trust Region Based Adversarial Attack on Neural Networks
Zhewei Yao, Amir Gholami, Peng Xu +2
Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tu…
Parameter Re-Initialization through Cyclical Batch Size Schedules
Norman Mu, Zhewei Yao, Amir Gholami +2
Optimal parameter initialization remains a crucial problem for neural network training. A poor weight initialization may take longer to train and/or converge to sub-optimal solutio…
On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent
Noah Golmant, Nikita Vemuri, Zhewei Yao +5
Increasing the mini-batch size for stochastic gradient descent offers significant opportunities to reduce wall-clock training time, but there are a variety of theoretical and syste…
A Novel Domain Adaptation Framework for Medical Image Segmentation
Amir Gholami, Shashank Subramanian, Varun Shenoy +6
We propose a segmentation framework that uses deep neural networks and introduce two innovations. First, we describe a biophysics-based domain adaptation method. Second, we propose…
Simulation of glioblastoma growth using a 3D multispecies tumor model with mass effect
Shashank Subramanian, Amir Gholami, George Biros
In this article, we present a multispecies reaction-advection-diffusion partial differential equation (PDE) coupled with linear elasticity for modeling tumor growth. The model aims…
Large batch size training of neural networks with adversarial training and second-order information
Zhewei Yao, Amir Gholami, Daiyaan Arfeen +4
The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep…
CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration
Andreas Mang, Amir Gholami, Christos Davatzikos +1
With this work, we release CLAIRE, a distributed-memory implementation of an effective solver for constrained large deformation diffeomorphic image registration problems in three d…
Co-Design of Deep Neural Nets and Neural Net Accelerators for Embedded Vision Applications
Kiseok Kwon, Alon Amid, Amir Gholami +3
Deep Learning is arguably the most rapidly evolving research area in recent years. As a result it is not surprising that the design of state-of-the-art deep neural net models proce…
SqueezeNext: Hardware-Aware Neural Network Design
Amir Gholami, Kiseok Kwon, Bichen Wu +5
One of the main barriers for deploying neural networks on embedded systems has been large memory and power consumption of existing neural networks. In this work, we introduce Squee…
PDE-constrained optimization in medical image analysis
Andreas Mang, Amir Gholami, Christos Davatzikos +1
PDE-constrained optimization problems find many applications in medical image analysis, for example, neuroimaging, cardiovascular imaging, and oncological imaging. We review relate…
Hessian-based Analysis of Large Batch Training and Robustness to Adversaries
Zhewei Yao, Amir Gholami, Qi Lei +2
Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not comple…