no code implementations • 20 Nov 2020 • Chengming Zhang, Geng Yuan, Wei Niu, Jiannan Tian, Sian Jin, Donglin Zhuang, Zhe Jiang, Yanzhi Wang, Bin Ren, Shuaiwen Leon Song, Dingwen Tao
Moreover, compared with the state-of-the-art pruning-during-training approach, ClickTrain provides significant improvements both accuracy and compression ratio on the tested CNN models and datasets, under similar limited training time.
no code implementations • 18 Nov 2020 • Sian Jin, Guanpeng Li, Shuaiwen Leon Song, Dingwen Tao
In this paper, we propose a novel memory-driven high performance DNN training framework that leverages error-bounded lossy compression to significantly reduce the memory requirement for training in order to allow training larger networks.
no code implementations • 4 Apr 2021 • Xiangyu Gao, Sumit Roy, Guanbin Xing, Sian Jin
Millimeter-wave (mmWave) radars are being increasingly integrated in commercial vehicles to support new Adaptive Driver Assisted Systems (ADAS) features that require accurate location and Doppler velocity estimates of objects, independent of environmental conditions.
no code implementations • 25 May 2021 • Jinyang Liu, Sheng Di, Kai Zhao, Sian Jin, Dingwen Tao, Xin Liang, Zizhong Chen, Franck Cappello
(1) We provide an in-depth investigation of the characteristics of various autoencoder models and develop an error-bounded autoencoder-based framework in terms of the SZ model.
no code implementations • 22 May 2022 • Liu Cao, Lyutianyang Zhang, Sian Jin, Sumit Roy
As most existing work investigate the PHY layer abstraction under an assumption of perfect channel estimation, it may become unreliable if there exists channel estimation error in a real communication system.
no code implementations • 1 Nov 2022 • Baixi Sun, Xiaodong Yu, Chengming Zhang, Jiannan Tian, Sian Jin, Kamil Iskra, Tao Zhou, Tekin Bicer, Pete Beckman, Dingwen Tao
Our evaluation with three scientific surrogates and 32 GPUs illustrates that SOLAR can achieve up to 24. 4X speedup over PyTorch Data Loader and 3. 52X speedup over state-of-the-art data loaders.
no code implementations • 6 Apr 2023 • Sian Jin, Pu Perry Wang, Petros Boufounos, Philip V. Orlik, Ryuhei Takahashi, Sumit Roy
We also derive analytical closed-form expressions for probabilities of detection and false alarm.
no code implementations • 7 Sep 2023 • Jinyang Liu, Sheng Di, Sian Jin, Kai Zhao, Xin Liang, Zizhong Chen, Franck Cappello
The fast growth of computational power and scales of modern super-computing systems have raised great challenges for the management of exascale scientific data.
no code implementations • 20 Apr 2024 • Wenqi Jia, Sian Jin, Jinzhen Wang, Wei Niu, Dingwen Tao, Miao Yin
Leveraging a group of neural networks, GWLZ significantly enhances the decompressed data reconstruction quality with negligible impact on the compression efficiency.
1 code implementation • 18 Nov 2021 • Sian Jin, Chengming Zhang, Xintong Jiang, Yunhe Feng, Hui Guan, Guanpeng Li, Shuaiwen Leon Song, Dingwen Tao
In this paper, we propose a novel memory-efficient CNN training framework (called COMET) that leverages error-bounded lossy compression to significantly reduce the memory requirement for training, to allow training larger models or to accelerate training.
1 code implementation • 26 Jan 2019 • Sian Jin, Sheng Di, Xin Liang, Jiannan Tian, Dingwen Tao, Franck Cappello
In this paper, we propose DeepSZ: an accuracy-loss bounded neural network compression framework, which involves four key steps: network pruning, error bound assessment, optimization for error bound configuration, and compressed model generation, featuring a high compression ratio and low encoding time.
2 code implementations • 19 Jul 2020 • Jiannan Tian, Sheng Di, Kai Zhao, Cody Rivera, Megan Hickman Fulp, Robert Underwood, Sian Jin, Xin Liang, Jon Calhoun, Dingwen Tao, Franck Cappello
To the best of our knowledge, cuSZ is the first error-bounded lossy compressor on GPUs for scientific data.
Distributed, Parallel, and Cluster Computing