About me

I am a Postdoc in Industrial and System Engineering at the University of Southern California. I received my Ph.D. in Electrical Engineering in 2023 and my M.Eng. in Electrical Engineering in 2022 at the University of Minnesota. I received my B.E. in Automation from the University of Science and Technology of China in 2018. Please see my CV for more details.

Research Interests

My research interest is in the theoretical aspect of distributed optimization and differential privacy for machine learning. My recent work focuses on:

  1. designing differentially private optimization algorithms with theoretical guarantees.
  2. understanding distributed optimization algorithms, designing system-specific algorithms, and making connections to signal processing and control theory.
  3. understanding federated learning from different perspectives and resolving existing problems in federated learning, including data heterogeneity, communication efficiency, and differential privacy.

For more details, please see my publications.

News

  • September 2024, two papers accepted by NeurIPS 2024:
    • Pre-training Differentially Private Models with Limited Public Data, with Zhiqi Bu, Sheng Zha, Mingyi Hong, and George Karypis, see here.
    • DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction, with Zhiqi Bu, Mingyi Hong, and Meisam Razaviyayn, see here.