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:

  1. designing efficient and scalable optimizers for pretraining and post-training of Large Language Models;

  2. explaining the practical efficiency of optimization algorithms from a theoretical perspective.
My featured work ⭐ takes a small but meaningful step toward these goals. Feel free to reach out if you are also excited about optimization and LLMs.

Preprints

  1. StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models [arXiv] ⭐
    Dingzhi Yu*, Rui Pan*, Yuxing Liu*, and Tong Zhang (* denotes equal contribution)

  2. Sign-Based Optimizers Are Effective Under Heavy-Tailed Noise [arXiv, Code] ⭐
    Dingzhi Yu, Hongyi Tao, Yuanyu Wan, Luo Luo, and Lijun Zhang

  3. When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\ell_1$-norm Lower Bounds [arXiv, Code]
    Hongyi Tao*, Dingzhi Yu*, and Lijun Zhang

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

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

  6. Improved Approximate Regret for Decentralized Online Continuous Submodular Maximization via Reductions [arXiv]
    Yuanyu Wan, Yu Shen, Dingzhi Yu, Bo Xue, and Mingli Song

Publication

  1. Mirror Descent Under Generalized Smoothness [arXiv]
    Dingzhi Yu, Wei Jiang, Hongyi Tao, Yuanyu Wan, and Lijun Zhang
    In Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), to appear, 2026.

  2. 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.

Awards & Honors

Academic Service

Correspondence