no code implementations • 5 Jun 2023 • Trishita Tiwari, Suchin Gururangan, Chuan Guo, Weizhe Hua, Sanjay Kariyappa, Udit Gupta, Wenjie Xiong, Kiwan Maeng, Hsien-Hsin S. Lee, G. Edward Suh
In today's machine learning (ML) models, any part of the training data can affect its output.
no code implementations • 4 Mar 2022 • Yaohui Cai, Weizhe Hua, Hongzheng Chen, G. Edward Suh, Christopher De Sa, Zhiru Zhang
In addition, since PreCropping compresses CNNs at initialization, the computational and memory costs of CNNs are reduced for both training and inference on commodity hardware.
1 code implementation • 21 Feb 2022 • Weizhe Hua, Zihang Dai, Hanxiao Liu, Quoc V. Le
We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences.
Ranked #1 on Language Modelling on Wiki-40B
no code implementations • NeurIPS 2021 • Weizhe Hua, Yichi Zhang, Chuan Guo, Zhiru Zhang, G. Edward Suh
Neural network robustness has become a central topic in machine learning in recent years.
no code implementations • 27 May 2021 • Yanqi Zhang, Weizhe Hua, Zhuangzhuang Zhou, Edward Suh, Christina Delimitrou
Cloud applications are increasingly shifting from large monolithic services, to large numbers of loosely-coupled, specialized microservices.
no code implementations • 17 Nov 2020 • Qiwei Yuan, Weizhe Hua, Yi Zhou, Cunxi Yu
The minibatch stochastic gradient descent method (SGD) is widely applied in deep learning due to its efficiency and scalability that enable training deep networks with a large volume of data.
no code implementations • 26 Aug 2020 • Weizhe Hua, Muhammad Umar, Zhiru Zhang, G. Edward Suh
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment.
no code implementations • 20 Apr 2020 • Weizhe Hua, Muhammad Umar, Zhiru Zhang, G. Edward Suh
This paper introduces MGX, a near-zero overhead memory protection scheme for hardware accelerators.
1 code implementation • ICLR 2020 • Yichi Zhang, Ritchie Zhao, Weizhe Hua, Nayun Xu, G. Edward Suh, Zhiru Zhang
The proposed approach is applicable to a variety of DNN architectures and significantly reduces the computational cost of DNN execution with almost no accuracy loss.
1 code implementation • NeurIPS 2019 • Weizhe Hua, Yuan Zhou, Christopher De Sa, Zhiru Zhang, G. Edward Suh
Combining our method with knowledge distillation reduces the compute cost of ResNet-18 by 2. 6$\times$ without accuracy drop on ImageNet.