Hi there 😃. I am Tongtian Zhu (prounced as “Tong-tee-an Joo”), a second-year PhD student at the Computer Science Department of Zhejiang University (ZJU), supervised by Professors Mingli Song and Chun Chen. Before joining ZJU, I was a research intern at JD Explore Academy (JDE), working on the generalization theory of decentralized learning, mentored by Doctor Fengxiang He and Professor Dacheng Tao. My current research focuses on the theoretical aspects of decentralized learning. I am also dedicated to utilizing elegant theoretical insights to construct fast and generalizable decentralized learning algorithms.
🦄 Research Interest
“Seek truth and beauty.”
In the science aspect, my primary research interest lies in understanding the mechanisms underpining the practical success of deep learning. In the technology aspect, I am passionate about developing machine learning methodologies inspired by principles.
My current research focus include:
- Generalization Theory of Decentralized Learning.
- Developing Fast & Generalizable Decentralized Algorithms.
|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 Theory 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!
|Apr 25, 2023||
Our paper “Decentralized SGD and Average-direction SAM are Asymptotically Equivalent” is accpeted at ICML 2023!
|Feb 11, 2023||Our paper “Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition” is accpeted at AAAI 2023 (Oral)!|
|Dec 6, 2022||I am awarded as a Merit PhD student/Triple A PhD student of Zhejiang University on 2021-2022 (top 10%)!|
|May 17, 2022||Our paper “Topology-aware Generalization of Decentralized SGD” is accepted at ICML 2022 (Spotlight)!|
- ICML 2022 (Spotlight)Topology-aware Generalization of Decentralized SGDIn Proceedings of the 39th International Conference on Machine Learning, 17–23 jul 2022
- ICML 2023 (My Favorite)Decentralized SGD and Average-direction SAM are Asymptotically EquivalentIn Proceedings of the 40th International Conference on Machine Learning, 23–29 jul 2023
📚 Academic Services
- Conference Reviewer: ICLR 2024; ICML 2022, 2023; NeurIPS 2022, 2023; AISTATS 2023, 2024; UAI 2023; ECML 2023; ACML 2022.
- Journal Reviewer: Information Science.
- I am also a contributor of International Seminar on Foundational Artificial Intelligence (FAI-Seminar).
- 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). I practiced sketching for over five years. I used to have a strong desire to become a manga artist (“漫画家” in Chinese). I firmly believe that the aesthetic sensibility I have developed from studying fine arts is very beneficial to 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!