Xiaohan Chen

PhD Student

Electrical and Computer Engineering

University of Texas at Austin

About Me

Hi there! I am currently a senier algorithm engineer at Decision Intelligence Lab (DI) at DAMO Acedamy in Alibaba Group, in close collaboration with Dr. Wotao Yin. I obtained my Ph.D. degree in Electrical and Computer Engineering Department in 2022 at the University of Texas at Austin. I was fortunate to have worked in the Visual Informatics Group @ University of Texas at Austin (VITA Group) under the supervision of Prof. Zhangyang Wang. Prior to the start of my Ph.D. program, I obtained my B. S. degree from the School of Gifted Young, University of Science and Technology of China (USTC), in 2017.

My research focuses on large language models, learn-to-optimize, meta-learning and efficient deep learning, and sparse neural networks, recently in particular the lottery ticket hypothesis and network analysis in neural networks. Here is my CV.

Interests

Sparse Optimization
Learn to Optimize
Meta Learning
Efficient Deep Learning
Sparse Neural Networks

Education

ECE (DICE Track), 2020 - Present

University of Texas at Austin
Computer Science, 2017 - 2020

Texas A&M University
BSc in Applied Mathematics, 2017

University of Science and Technology of China
BEng in Computer Science (Double), 2017

University of Science and Technology of China

Recent Publications

* The authors contribute equally.

*X. Chen, *J. Liu, Z. Wang, W. Yin (2021). Hyperparameter Tuning is All You Need for LISTA. NeurIPS 2021.

X. Chen, Y. Cheng, S. Wang, Z. Gan, J. Liu, Z. Wang (2021). The Elastic Lottery Ticket Hypothesis. NeurIPS 2021.

Preprint PDF Code

S. Liu, T. Chen, X. Chen, Z. Atashgahi, L. Yin, H. Kou, L. Shen, M. Pechenizkiy, Z. Wang, D. M. Mocanu (2021). Sparse Training via Boosting Pruning Plasticity with Neuroregeneration. NeurIPS 2021.

X. Ma, G. Yuan, X. Shen, T. Chen, X. Chen, X. Chen, N. Liu, M. Qin, S. Liu, Z. Wang, Y. Wang (2021). Sanity Checks for Lottery Tickets: Does Your Winning Ticket Really Win the Jackpot?. NeurIPS 2021.

X. Chen, Y. Cheng, S. Wang, Z. Gan, Z. Wang, J. Liu (2021). EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets. ACL-IJCNLP 2021.

Preprint PDF Code Slides

T. Chen, X. Chen, W. Chen, H. Heaton, J. Liu, Z. Wang, W. Yin (2021). Learning to Optimize: A Primer and A Benchmark. arXiv pre-print, under review in JMLR.

Preprint PDF Code

*T. Meng, *X. Chen, Y. Jiang, Z. Wang (2021). A Design Space Study for LISTA and Beyond. ICLR 2021.

Project

*J. Shen, *X. Chen, H. Heaton, T. Chen, J. Liu, Z. Wang, Y. Lin (2021). Learning A Minimax Optimizer: A Pilot Study. ICLR 2021.

Project

*X. Chen, *Y. Zhao, Y. Wang, P. Xu, H. You, C. Li, Y. Fu, Y. Lin, Z. Wang (2020). SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training. Under review in TNNLS.

X. Chen, Z. Wang, S. Tang, K. Muandet (2020). MATE: Plugging in Model Awareness to Task Embedding for Meta Learning. NeurIPS 2020.

H. You, X. Chen, Y. Zhang, C. Li, S. Li, Z. Liu, Z. Wang, Y. Lin (2020). ShiftAddNet: A Hardware-Inspired Deep Network. NeurIPS 2020.

H. Heaton, X. Chen, Z. Wang, W. Yin (2020). Safeguarded Learned Convex Optimization. Under review in JMLR.

Preprint

Z. Huo, A. Pakbin, X. Chen, N. Hurley, Y. Yuan, X. Qian, Z. Wang, S. Huang, B. Mortazavi (2020). Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discovery. AISTATS 2020.

*X. Chen, *Y. Zhao, Y. Wang, C. Li, Y. Xie, Z. Wang, Y. Lin (2020). SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation . ISCA 2020.

H. You, C. Li, P. Xu, Y. Fu, X. Chen, Y. Lin, Z. Wang, R. Baraniuk (2020). Drawing Early-Bird Tickets: Toward More Efficient Training of Deep Networks. ICLR 2020.

Preprint PDF Project

*X. Chen, *Z. Jiang, *Y. Wang, P. Xu, Y. Zhao, Y. Lin, Z. Wang (2019). E2-Train: Energy-Efficient Deep Network Training with Data-, Model-, and Algorithm-Level Saving. NeurIPS 2019.

Preprint PDF Code Project

E. Ryu, J. Liu, S. Wang, X. Chen, Z. Wang, W. Yin (2019). Plug-and-Play Methods Provably Converge with Properly Trained Denoisers. ICML 2019.

Preprint PDF Code Project Slides Video

*X. Chen, *J. Liu, Z. Wang, W. Yin (2019). ALISTA: Analytic Weights Are As Good As Learned Weights in LISTA. ICLR 2019.

PDF Code Project Slides

*X. Chen, *J. Liu, Z. Wang, W. Yin (2018). Theoretical Linear Convergence of Unfolded ISTA and its Practical Weights and Thresholds. NeurIPS 2018, Spotlight Oral.

Preprint PDF Code Poster Slides Video

N. Bansal, X. Chen, Z. Wang (2018). Can We Gain More from Orthogonality Regularizations in Training Deep Networks?. NeurIPS 2018.

Preprint PDF Code Poster Video