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 Xiaohan Chen

The Elastic Lottery Ticket Hypothesis


Mar 30, 2021
Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Jingjing Liu, Zhangyang Wang


  Access Paper or Ask Questions

Learning to Optimize: A Primer and A Benchmark


Mar 23, 2021
Tianlong Chen, Xiaohan Chen, Wuyang Chen, Howard Heaton, Jialin Liu, Zhangyang Wang, Wotao Yin


  Access Paper or Ask Questions

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training


Jan 04, 2021
Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang

* arXiv admin note: substantial text overlap with arXiv:2005.03403 

  Access Paper or Ask Questions

EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets


Dec 31, 2020
Xiaohan Chen, Yu Cheng, Shuohang Wang, Zhe Gan, Zhangyang Wang, Jingjing Liu


  Access Paper or Ask Questions

ShiftAddNet: A Hardware-Inspired Deep Network


Oct 24, 2020
Haoran You, Xiaohan Chen, Yongan Zhang, Chaojian Li, Sicheng Li, Zihao Liu, Zhangyang Wang, Yingyan Lin

* Accepted by NeurIPS 2020 

  Access Paper or Ask Questions

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation


May 08, 2020
Yang Zhao, Xiaohan Chen, Yue Wang, Chaojian Li, Haoran You, Yonggan Fu, Yuan Xie, Zhangyang Wang, Yingyan Lin

* Accepted by 47th International Symposium on Computer Architecture (ISCA'2020) 

  Access Paper or Ask Questions

Safeguarded Learned Convex Optimization


Mar 04, 2020
Howard Heaton, Xiaohan Chen, Zhangyang Wang, Wotao Yin


  Access Paper or Ask Questions

Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery


Mar 03, 2020
Zepeng Huo, Arash PakBin, Xiaohan Chen, Nathan Hurley, Ye Yuan, Xiaoning Qian, Zhangyang Wang, Shuai Huang, Bobak Mortazavi

* 10 pages, 5 figures, accepted by AISTATS 2020 

  Access Paper or Ask Questions

E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings


Dec 06, 2019
Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang


  Access Paper or Ask Questions

E2-Train: Training State-of-the-art CNNs with Over 80% Less Energy


Nov 06, 2019
Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang


  Access Paper or Ask Questions

E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving


Oct 29, 2019
Yue Wang, Ziyu Jiang, Xiaohan Chen, Pengfei Xu, Yang Zhao, Yingyan Lin, Zhangyang Wang


  Access Paper or Ask Questions

Drawing early-bird tickets: Towards more efficient training of deep networks


Sep 26, 2019
Haoran You, Chaojian Li, Pengfei Xu, Yonggan Fu, Yue Wang, Xiaohan Chen, Yingyan Lin, Zhangyang Wang, Richard G. Baraniuk


  Access Paper or Ask Questions

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers


May 14, 2019
Ernest K. Ryu, Jialin Liu, Sicheng Wang, Xiaohan Chen, Zhangyang Wang, Wotao Yin

* Published in the International Conference on Machine Learning, 2019 

  Access Paper or Ask Questions

Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds


Nov 04, 2018
Xiaohan Chen, Jialin Liu, Zhangyang Wang, Wotao Yin

* 18 pages, 6 figures, 1 table. Accepted as spotlight oral in NIPS 2018 

  Access Paper or Ask Questions

Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?


Oct 22, 2018
Nitin Bansal, Xiaohan Chen, Zhangyang Wang

* 11 pages, 1 figure, 2 tables. Accepted in NIPS 2018 

  Access Paper or Ask Questions