Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Amir Gholami

Q-ASR: Integer-only Zero-shot Quantization for Efficient Speech Recognition


Mar 31, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Anirudda Nrusimha, Bohan Zhai, Tianren Gao, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

A Survey of Quantization Methods for Efficient Neural Network Inference


Mar 25, 2021
Amir Gholami, Sehoon Kim, Zhen Dong, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer

* Book Chapter: Low-Power Computer Vision: Improving the Efficiency of Artificial Intelligence 

  Access Paper or Ask Questions

I-BERT: Integer-only BERT Quantization


Feb 11, 2021
Sehoon Kim, Amir Gholami, Zhewei Yao, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Hessian-Aware Pruning and Optimal Neural Implant


Feb 06, 2021
Shixing Yu, Zhewei Yao, Amir Gholami, Zhen Dong, Michael W Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

HAWQV3: Dyadic Neural Network Quantization


Nov 20, 2020
Zhewei Yao, Zhen Dong, Zhangcheng Zheng, Amir Gholami, Jiali Yu, Eric Tan, Leyuan Wang, Qijing Huang, Yida Wang, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Boundary thickness and robustness in learning models


Jul 09, 2020
Yaoqing Yang, Rajiv Khanna, Yaodong Yu, Amir Gholami, Kurt Keutzer, Joseph E. Gonzalez, Kannan Ramchandran, Michael W. Mahoney


  Access Paper or Ask Questions

ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning


Jun 01, 2020
Zhewei Yao, Amir Gholami, Sheng Shen, Kurt Keutzer, Michael W. Mahoney


  Access Paper or Ask Questions

Rethinking Batch Normalization in Transformers


Mar 17, 2020
Sheng Shen, Zhewei Yao, Amir Gholami, Michael Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

PyHessian: Neural Networks Through the Lens of the Hessian


Jan 02, 2020
Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney


  Access Paper or Ask Questions

ZeroQ: A Novel Zero Shot Quantization Framework


Jan 01, 2020
Yaohui Cai, Zhewei Yao, Zhen Dong, Amir Gholami, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks


Nov 10, 2019
Zhen Dong, Zhewei Yao, Yaohui Cai, Daiyaan Arfeen, Amir Gholami, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Checkmate: Breaking the Memory Wall with Optimal Tensor Rematerialization


Oct 07, 2019
Paras Jain, Ajay Jain, Aniruddha Nrusimha, Amir Gholami, Pieter Abbeel, Kurt Keutzer, Ion Stoica, Joseph E. Gonzalez


  Access Paper or Ask Questions

Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT


Sep 25, 2019
Sheng Shen, Zhen Dong, Jiayu Ye, Linjian Ma, Zhewei Yao, Amir Gholami, Michael W. Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

ANODEV2: A Coupled Neural ODE Evolution Framework


Jun 10, 2019
Tianjun Zhang, Zhewei Yao, Amir Gholami, Kurt Keutzer, Joseph Gonzalez, George Biros, Michael Mahoney


  Access Paper or Ask Questions

HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision


Apr 29, 2019
Zhen Dong, Zhewei Yao, Amir Gholami, Michael Mahoney, Kurt Keutzer


  Access Paper or Ask Questions

Inefficiency of K-FAC for Large Batch Size Training


Mar 14, 2019
Linjian Ma, Gabe Montague, Jiayu Ye, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael W. Mahoney


  Access Paper or Ask Questions

ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs


Feb 27, 2019
Amir Gholami, Kurt Keutzer, George Biros


  Access Paper or Ask Questions

Trust Region Based Adversarial Attack on Neural Networks


Dec 16, 2018
Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael Mahoney


  Access Paper or Ask Questions

Parameter Re-Initialization through Cyclical Batch Size Schedules


Dec 04, 2018
Norman Mu, Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney

* Presented in Systems for Machine Learning Workshop at NeurIPS'18 conference 

  Access Paper or Ask Questions

On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent


Nov 30, 2018
Noah Golmant, Nikita Vemuri, Zhewei Yao, Vladimir Feinberg, Amir Gholami, Kai Rothauge, Michael W. Mahoney, Joseph Gonzalez


  Access Paper or Ask Questions

A Novel Domain Adaptation Framework for Medical Image Segmentation


Oct 11, 2018
Amir Gholami, Shashank Subramanian, Varun Shenoy, Naveen Himthani, Xiangyu Yue, Sicheng Zhao, Peter Jin, George Biros, Kurt Keutzer


  Access Paper or Ask Questions

Large batch size training of neural networks with adversarial training and second-order information


Oct 02, 2018
Zhewei Yao, Amir Gholami, Kurt Keutzer, Michael Mahoney

* 17 pages 

  Access Paper or Ask Questions

SqueezeNext: Hardware-Aware Neural Network Design


Aug 27, 2018
Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter Jin, Sicheng Zhao, Kurt Keutzer

* 12 Pages 

  Access Paper or Ask Questions

CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration


Aug 13, 2018
Andreas Mang, Amir Gholami, Christos Davatzikos, George Biros


  Access Paper or Ask Questions

Hessian-based Analysis of Large Batch Training and Robustness to Adversaries


Jun 18, 2018
Zhewei Yao, Amir Gholami, Qi Lei, Kurt Keutzer, Michael W. Mahoney

* 23 pages, 16 figures 

  Access Paper or Ask Questions

Integrated Model, Batch and Domain Parallelism in Training Neural Networks


May 16, 2018
Amir Gholami, Ariful Azad, Peter Jin, Kurt Keutzer, Aydin Buluc

* 30th ACM Symposium on Parallelism in Algorithms and Architectures (SPAA), 2018 
* 11 pages 

  Access Paper or Ask Questions