Hao Zhang

Email: sjtu.haozhang AT


I will be moving to the RISE Lab at the University of California, Berkeley as a postdoctoral scholar, working with Prof. Ion Stoica.

My most recent project is building an end-to-end composable and automated stack for large-scale distributed DL. The two most relevant projects are: AutoDist for automatic ML parallelization, and AdaptDL for co-adaptive ML job scheduling.

My general research interest is in scalable machine learning, deep learning, and large-scale ML applications in computer vision and natural language processing. I co-design models, algorithms, and systems to scale out ML to larger data, problems and applications, to ease the prototyping of complex ML models and algorithms, and to automate the distribution of ML programs.

I completed my Ph.D. in the Robotics Institute, Carnegie Mellon University. My advisor was Prof. Eric Xing. My Ph.D. thesis is Machine Learning Parallelism Could Be Adaptive, Composable and Automated. Several of my Ph.D. works including Poseidon, Cavs, and GeePS, are parts of the Petuum project, and now being commercialized at the Pittsburgh-based startup Petuum Inc.



[ / / / / / ]

Hao Zhang, Peng Wu, Christy Li, Zhijie Deng, Aurick Qiao, Zeya Wang, Qirong Ho,
Eric P. Xing
Preprint 2020, to appear
Aurick Qiao, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger,
Eric P. Xing
Preprint 2020
arXiv code
Hao Zhang, Christy Li, Zhijie Deng, Xiaodan Liang, Lawrence Carin, Eric P. Xing
NeurIPS 2020, To appear
Zhijie Deng, Xiao Yang, Hao Zhang, Yinpeng Dong, Jun Zhu
Preprint 2020
arXiv code
Hao Zhang*, Haowen Xu*, Zhiting Hu, Xiaodan Liang, Qirong Ho,
Eric P. Xing (* indicates equal contributions)
ICLR 2019
arXiv code
Wei Dai, Yi Zhou, Nanqing Dong, Hao Zhang, Eric P. Xing
ICLR 2019
Hao Zhang*, Shizhen Xu*, Graham Neubig, Wei Dai, Qirong Ho, Guangwen Yang,
Eric P. Xing (* indicates equal contributions)
ATC 2018 (Oral), AISys@SOSP 2017, MLSys@NeurIPS 2017
arXiv slides code medium post
Hao Zhang*, Zhijie Deng*, Xiaodan Liang, Luona Yang, Shizhen Xu, Jun Zhu,
Eric P. Xing (* indicates equal contributions)
NeurIPS 2017(Nvidia Pioneer Research Award!)
arXiv code
Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu,
Jinliang Wei, Pengtao Xie, Eric P. Xing
ATC 2017 (Oral)
arXiv slides project zhihu post (in Chinese)
Henggang Cui, Hao Zhang, Gregory R. Ganger, Phillip B. Gibbons, Eric P. Xing
EuroSys 2016
slides code
Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis DeCoste,
Wei Di, Yizhou Yu
ICCV 2015
arXiv project