I'm a postdoc researcher in the Statistics Department, Wharton School,
University of Pennsylvania.
Prior to Penn, I was a research scientist in Facebook from 2017 to 2019.
With my teammates, I help Facebook build its distributed training system
for training deep personalization and recommendation models. My work
concentrates on distributed optimization algorithms and system
I received my PhD degree in CS at the University of Chicago in 2017. I
was very fortunate to be advised by Prof. John Lafferty.
During my PhD, I worked in the intersection of machine learning,
optimization and statistics. My research centered around developing
novel computationally efficient methods with theoretical guarantees for
challenging machine learning problems, with an emphasis on finding exact
solutions for nonconvex problems.
Earlier, I got my master degree in Max Planck Institute for Informatics
and my bachelor degree in Zhejiang University.
Publication and Preprint
Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
Jinshuo Dong, Qi Long, Weijie Su
ShadowSync: Performing Synchronization in the Background for Highly Scalable Distributed Training
Qinqing Zheng, Bor-Yiing Su, Jiyan Yang, Alisson Azzolini, Qiang Wu, Ou Jin, Shri Karandikar, Hagay Lupesko, Liang Xiong, Eric Zhou