Haiyun He

(Pronunciation: /ˈhaɪyuːŋ ˈhɜː/,   Pronouns: she/her/hers)
Postdoc Associate, Center for Applied Mathematics, Cornell University

prof_pic.jpg

(Taken at Cornell Slope)

Hi! I am currently a postdoc at Cornell University, working with Prof. Ziv Goldfeld from ECE and Prof. Christina Lee Yu from ORIE. I am honored to be funded by the Center for Applied Mathematics postdoctoral fellowship. Before joining Cornell, I obtained my PhD degree in Electrical and Computer Engineering from National University of Singapore in Sep. 2022, advised by Prof. Vincent Y. F. Tan.

My recent research interests lie in the intersection of information theory and machine learning, including but not limited to:

  • Machine learning and statistical learning theory
  • Hypothesis testing
  • Inference and estimation
  • Wireless communications

If you are interested in collaborating with me, please do not hesitate to drop me an email (at the bottom) or drop by  657 Rhodes Hall, Ithaca, NY  !

⭐ I am on the 2024-2025 academic job market. Please feel free to reach out!

News

09/09/2024 Going to attend Workshop II: Theory and Practice of Deep Learning at IPAM, UCLA between Oct. 14-18.
08/30/2024 Invited to give a talk about our recent work in the Math Department of Wayne State University on Oct. 02, 2024 (Wednesday, 02:30 - 03:30 pm in FAB 1146). Thank Prof. Yan Wang and Prof. Rohini Kumar for the invitation!
04/09/2024 One paper (part of our recent work) accepted to ISIT 2024 in Athens, Greece. Prof. Ziv Goldfeld will be presenting our work in Athens. Say Hi to him!

Recent publications

  1. Universally Optimal Watermarking Schemes for LLMs: from Theory to Practice
    Haiyun He*, Yepeng Liu*, Ziqiao Wang, Yongyi Mao, and Yuheng Bu
    Submitted, Oct 2024
  2. Information-Theoretic Generalization Bounds for Deep Neural Networks
    Haiyun He, Christina Lee Yu, and Ziv Goldfeld
    Full-length version submitted, Apr 2024
  3. Journal
    Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning
    Haiyun He, Hanshu Yan, and Vincent Y. F. Tan
    Journal of Machine Learning Research, Aug 2022