I am a quantitative researcher at Citadel Securities. My research covers machine learning, statistics, and optimization.
Previously, I got my Ph.D. in Statistics from UC Berkeley, where I was fortunate to be advised by Michael I. Jordan and Martin J. Wainwright. During my graduate study, I was a member in the Berkeley Artificial Intelligence Research (BAIR) Lab. I also did several internships at Citadel Securities, Ant Financial, and Microsoft Research. I completed a B.Sc. with honors in Mathematics at the University of Hong Kong, where I completed my undergraduate theses with Ngaiming Mok in complex geometry and with Guangyue Han in coding and information theory. I was born and grew up in Shanghai, China.
Ph.D. in Statistics, 2015-2019
University of California, Berkeley
B.Sc. in Mathematics, 2012-2015
The University of Hong Kong
Exchange Study, Fall 2013
University of California, Berkeley
Citadel Securities
Sep. 2019 - Present
New York, NY
Citadel Securities
June 2018 - Sep. 2018
Chicago, IL
Ant Financial
Dec. 2017 - Jan. 2018
Hangzhou, China
UC Berkeley
Fall 2017
Berkeley, CA
Microsoft Research
Summer 2017
Redmond, WA
We focus on feature selection and instancewise feature selection as approaches for model interpretation.
We design systematic methods to evaluate and improve the robustness of machine learning models.
We design algorithms for hypothesis testing on graphs and networks that control false discovery rate.
We design models for editing images based on language description.
We study variance reduction in stochastic gradient optimization.
Talk on HopSkipJumpAttack: A Query-Efficient Decision-Based Attack.
Oral and Poster on LS-Tree: Model Interpretation When the Data Are Linguistic.
Spotlight Talk and Poster on ML-LOO: Detecting Adversarial Examples with Feature Attribution.
Talk on model interpretation and adversarial robustness.
Talk on model interpretation and adversarial robustness.
Poster on L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data.
Oral and Poster on Learning to Explain: An Information-Theoretic Perspective on Model Interpretation.
Spotlight Talk and Poster on Language-based Image Editing with Recurrent Attentive Models.
Poster on Kernel Feature Selection via Conditional Covariance Minimization.
Poster on Nonconvex Finite-Sum Optimization Via SCSG Methods.
Talk on FDR control on directed acyclic graphs.
Poster on Decentralized decision making on networks with FDR control.
Citadel Fellowship for 2018-2019.
Berkeley Fellowship for 2015-2017.
Ho Sin Hang Prize in Science for 2015.
Y.M. Chen Memorial Prize in Mathematics for 2015.
B.Sc. Class of 1971 Prize for 2014.
Wong Yung Chow Prize in Mathematics for 2014.
Ho Fook Prize for 2013.
Walter Brown Memorial Prizes in Mathematics for 2013.