Dynamic Gradient Sparse Update for Edge Training

Dynamic Gradient Sparse Update for Edge Training

International Symposium on Circuits and Systems (ISCAS), 2024

23 March 2025

Tian-Sheuan Chang

ArXiv (abs)PDF HTML

Papers citing "Dynamic Gradient Sparse Update for Edge Training"

15 / 15 papers shown

Title
VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale Zhiwei Hao Jianyuan Guo Kai Han Han Hu Chang Xu Yunhe Wang 142 19 0 25 May 2023
DepGraph: Towards Any Structural PruningComputer Vision and Pattern Recognition (CVPR), 2023 Gongfan Fang Xinyin Ma Weilong Dai Michael Bi Mi Xinchao Wang GNN 347 393 0 30 Jan 2023
NoMorelization: Building Normalizer-Free Models from a Sample's Perspective Yu Xie Yuwen Yang Yue Ding Hongtao Lu 204 2 0 13 Oct 2022
On-Device Training Under 256KB MemoryNeural Information Processing Systems (NeurIPS), 2022 Ji Lin Ligeng Zhu Wei-Ming Chen Wei-Chen Wang Chuang Gan Song Han MQ 345 254 0 30 Jun 2022
Zebra: Memory Bandwidth Reduction for CNN Accelerators With Zero Block Regularization of Activation MapsInternational Symposium on Circuits and Systems (ISCAS), 2020 Hsu-Tung Shih Tian-Sheuan Chang 116 3 0 02 May 2022
Unlearnable Examples: Making Personal Data UnexploitableInternational Conference on Learning Representations (ICLR), 2021 Hanxun Huang Jiabo He S. Erfani James Bailey Yisen Wang MIACV 454 230 0 13 Jan 2021
TinyTL: Reduce Activations, Not Trainable Parameters for Efficient On-Device Learning Han Cai Chuang Gan Ligeng Zhu Song Han 174 60 0 22 Jul 2020
Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNsInternational Conference on Learning Representations (ICLR), 2020 Jonathan Frankle D. Schwab Ari S. Morcos 263 156 0 29 Feb 2020
PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight PruningInternational Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2020 Wei Niu Xiaolong Ma Sheng Lin Shihao Wang Xuehai Qian Xinyu Lin Yanzhi Wang Bin Ren MQ 469 245 0 01 Jan 2020
Filter Response Normalization Layer: Eliminating Batch Dependence in the Training of Deep Neural NetworksComputer Vision and Pattern Recognition (CVPR), 2019 Saurabh Singh Shankar Krishnan UQCV 202 131 0 21 Nov 2019
The State of Sparsity in Deep Neural Networks Trevor Gale Erich Elsen Sara Hooker 337 829 0 25 Feb 2019
Revisiting Small Batch Training for Deep Neural Networks Dominic Masters Carlo Luschi ODL 141 722 0 20 Apr 2018
Group Normalization Yuxin Wu Kaiming He 487 4,061 0 22 Mar 2018
Channel Pruning for Accelerating Very Deep Neural Networks Yihui He Xiangyu Zhang Jian Sun 604 2,664 0 19 Jul 2017
CNN Features off-the-shelf: an Astounding Baseline for Recognition A. Razavian Hossein Azizpour Josephine Sullivan S. Carlsson 417 5,046 0 23 Mar 2014