Tongtian Zhu

"Convince future generations, not just peers."

photo_10.jpg

At the gorgeous Westlake, Hangzhou

Hi there 😃. I am Tongtian Zhu (prounced as “Tong-tee-an Joo”), a Ph.D. candidate at the Computer Science Department of Zhejiang University (ZJU), supervised by Professors Can Wang and Chun Chen. I am open to both academic and industry opportunities. If you have matched opportunities, questions, or are interested in collaborating, or just want to chat, please always feel free to contact me via email or WeChat.

Google Scholar    Twitter    Email    WeChat   

 

🦄 Research Interest

“Seek truth and beauty.”

My primary research interest lies in understanding the fundamental mechanisms underpinning the practical success of deep learning, including LLMs. I am also interested in developing machine learning methodologies inspired by principles.

My current research focus includes:

🔥 News

Apr 24, 2025 I’ll be in Singapore 🦁🌴 this April for ICLR 2025! Can’t wait to meet new and old friends. Ping me if you’d like to chat ☕️!
Jan 23, 2025 Our paper “DICE: Data Influence Cascade in Decentralized Learning” (🔗twitter threads, project page, video-Chinese, video-English) is accpeted at ICLR 2025 🎉!
DSGD-SAM
Jul 20, 2024 Very excited to attend ICML this time 😀! Feel free to reach out if you want to chat ☕️, whether it’s about deep learning theory (generalization, symmetries, training dynamics), decentralized learning (decentralized economies, privacy), or anything else.✨
Jul 12, 2023 I give a long talk (video, slides) at Beijing Academy of Artificial Intelligence (智源社区, BAAI) about our DSGD-SAM paper!
Jul 11, 2023 I give a long talk at the Deep Learning and Optimization Seminar in Westlake University on the generalization benefits of decentralization!
Jul 8, 2023 I give a talk at the Sixth World Artificial Intelligence Conference (第六届世界人工智能大会, WAIC) on the generalization benefits of decentralization!
WAIC
Apr 25, 2023 Our paper “Decentralized SGD and Average-direction SAM are Asymptotically Equivalent” is accpeted at ICML 2023!
DSGD-SAM
Feb 11, 2023 Our paper “Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition” is accpeted at AAAI 2023 (Oral)!
May 17, 2022 Our paper “Topology-aware Generalization of Decentralized SGD” is accepted at ICML 2022 (Spotlight)!

📝 Selected Publications

  1. ICLR 2025
    DICE: Data Influence Cascade in Decentralized Learning
    Tongtian Zhu, Wenhao Li, Can Wang, and Fengxiang He
    In International Conference on Learning Representations, 2025
  2. ICML 2023
    Decentralized SGD and Average-direction SAM are Asymptotically Equivalent
    Tongtian ZhuFengxiang HeKaixuan Chen, Mingli Song, and Dacheng Tao
    In Proceedings of the 40th International Conference on Machine Learning, 2023
  3. ICML 2022 (Spotlight)
    Topology-aware Generalization of Decentralized SGD
    Tongtian ZhuFengxiang HeLan ZhangZhengyang Niu, Mingli Song, and Dacheng Tao
    In Proceedings of the 39th International Conference on Machine Learning, 2022

📚 Academic Services

🤗 Miscellaneous

  • I am an (old-school) ACG fan. My favorites range from Detective Conan and Pokemon to Attack on Titan.
  • I was an amateur artist (or more accurately, an enthusiast), spending more than five years practicing my sketching skills. My dream was to become a manga artist ("漫画家" in Chinese). I firmly believe that he aesthetic sensibility nurtured through my fine arts studies considerably enhances my research.
  • I'm also a huge basketball fanatic! I have a profound love for basketball, particularly for the intrinsic beauty of the sport itself. I'm planning (possibly in 1 or 2 years) to start a blog series about the basics of basketball (e.g., rules, skills and tactics) through the lens of scientific research. Any comments are welcome!