Jinshuo Dong

About me: I just got my PhD in applied math (AMCS) from the University of Pennsylvania, under the super(b)vision of Aaron Roth. Prior to Penn, I obtained my bachelor's degree in mathematics from Peking University in 2014. My CV can be found here. Contact: Email: first name@sas.upenn.edu 3401 Walnut Street, Room 409B Philadelphia, PA 19104 News: I will be joining Northwestern University and TTI Chicago as an IDEAL postdoctoral fellow. Our paper Gaussian Differential Privacy was accepted by Journal of the Royal Statistical Society: Series B (JRSSB) as a discussion paper!

Research

Current focus of my work is differential privacy and its role in statistics and machine learning. I'm also generally interested in expanding my knowledge in the mathematics of information and computation.

Papers

• Gaussian Differential Privacy
  Jinshuo Dong, Aaron Roth and Weijie Su.
  Accepted as a discussion paper by Journal of the Royal Statistical Society: Series B (JRSSB)
  [blog post] [arXiv] [talk at Simons Institute]

• Deep Learning with Gaussian Differential Privacy
  Zhiqi Bu, Jinshuo Dong, Qi Long and Weijie Su.
  In submission.
  [blog post] [arXiv] [talk at PriML Workshop of NeurIPS 2019].

• Optimal Differential Privacy Composition for Exponential Mechanisms
  Jinshuo Dong, David Durfee and Ryan Rogers.
  To appear in ICML 2020.
  [blog post] [arXiv]
  

• Sharp Composition Bounds for Gaussian Differential Privacy via Edgeworth Expansion
  Qinqing Zheng, Jinshuo Dong, Qi Long, and Weijie Su.
  To appear in ICML 2020.
  [arXiv]

• Equilibrium Characterization for Data Acquisition Games.
  Jinshuo Dong, Hadi Elzayn, Shahin Jabbari, Michael Kearns and Zachary Schutzman.
  In the proceedings of IJCAI 2019.
  [arXiv]

• Strategic Classification from Revealed Preferences
  Jinshuo Dong, Aaron Roth, Zachary Schutzman, Bo Waggoner and Steven Wu.
  In the proceedings of EC 2018.
  [arXiv]