Dingzhi Yu | CS @ LAMDA-NJU

traunsee.JPG 

Dingzhi Yu (余 定 之)
M.Sc. student, LAMDA Group
Supervisor: Professor Lijun Zhang
Major: Computer Science and Technology
School of Artificial Intelligence
National Key Laboratory for Novel Software Technology
Nanjing University, Nanjing 210023, China

Google Scholar

About Me

I am a second-year graduate student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by Professor Zhi-Hua Zhou. Prior to that, I received my B.E. degree from School of Data Science, Fudan University in June 2024. Currently, I am a research intern at the University of Illinois Urbana-Champaign, under the valued supervision of Professor Tong Zhang.

I work on the interplay between optimization theory and modern machine learning, with the current focus on designing and explaining efficient optimizers for the post-training of Large Language Models.

Publication

  1. Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond [PDF, Bibtex]
    Dingzhi Yu, Yunuo Cai, Wei Jiang, and Lijun Zhang
    In Proceedings of the 41st International Conference on Machine Learning (ICML 2024), pages 57384-57414, 2024.

Preprints

  1. Improved Analysis for Sign-based Methods with Momentum Updates [arXiv]
    Wei Jiang, Dingzhi Yu, Sifan Yang, Wenhao Yang, and Lijun Zhang

  2. Group Distributionally Robust Optimization with Flexible Sample Queries [arXiv]
    Haomin Bai, Dingzhi Yu, Shuai Li, Haipeng Luo, and Lijun Zhang

  3. Mirror Descent Under Generalized Smoothness [arXiv]
    Dingzhi Yu, Wei Jiang, Yuanyu Wan, and Lijun Zhang

Awards & Honors

Academic Service

Correspondence