Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Hua, Weizhe"'
Autor:
Tiwari, Trishita, Gururangan, Suchin, Guo, Chuan, Hua, Weizhe, Kariyappa, Sanjay, Gupta, Udit, Xiong, Wenjie, Maeng, Kiwan, Lee, Hsien-Hsin S., Suh, G. Edward
In today's machine learning (ML) models, any part of the training data can affect the model output. This lack of control for information flow from training data to model output is a major obstacle in training models on sensitive data when access cont
Externí odkaz:
http://arxiv.org/abs/2306.03235
Pruning is a popular technique for reducing the model size and computational cost of convolutional neural networks (CNNs). However, a slow retraining or fine-tuning procedure is often required to recover the accuracy loss caused by pruning. Recently,
Externí odkaz:
http://arxiv.org/abs/2203.02549
We revisit the design choices in Transformers, and propose methods to address their weaknesses in handling long sequences. First, we propose a simple layer named gated attention unit, which allows the use of a weaker single-head attention with minima
Externí odkaz:
http://arxiv.org/abs/2202.10447
Cloud applications are increasingly shifting to interactive and loosely-coupled microservices. Despite their advantages, microservices complicate resource management, due to inter-tier dependencies. We present Sinan, a cluster manager for interactive
Externí odkaz:
http://arxiv.org/abs/2112.06254
Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common corruptions also introduce a large computational overhead, requiring as m
Externí odkaz:
http://arxiv.org/abs/2109.14707
Cloud applications are increasingly shifting from large monolithic services, to large numbers of loosely-coupled, specialized microservices. Despite their advantages in terms of facilitating development, deployment, modularity, and isolation, microse
Externí odkaz:
http://arxiv.org/abs/2105.13424
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. Particularly in the distributed setting, SGD is usually ap
Externí odkaz:
http://arxiv.org/abs/2011.08968
This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based protection for user data and model parameters even in an untrusted environment. GuardNN shows that the architecture and protection can be customized for a specific app
Externí odkaz:
http://arxiv.org/abs/2008.11632
This paper introduces MGX, a near-zero overhead memory protection scheme for hardware accelerators. MGX minimizes the performance overhead of off-chip memory encryption and integrity verification by exploiting the application-specific properties of t
Externí odkaz:
http://arxiv.org/abs/2004.09679
We propose precision gating (PG), an end-to-end trainable dynamic dual-precision quantization technique for deep neural networks. PG computes most features in a low precision and only a small proportion of important features in a higher precision to
Externí odkaz:
http://arxiv.org/abs/2002.07136