 |
Graduate Student 7th floor, Sutardja Dai Hall, Berkeley, CA 94720. |
About me
I am a final-year PhD student in the EECS department at UC Berkeley advised by Michael I. Jordan and Yi Ma. I obtained my B.S. from the Department of Mathematics at Nanjing University, and my M.S. from the Department of Computer Science, University of Virginia.
My research interests are broadly in theoretical foundations and applications of trustworthy machine learning. My current focus is on- Interpretable white-box deep neural networks [e.g., CRATE: white-box transformer];
- Differentially private foundation models [e.g., ViP: A Differentially Private Vision Foundation Model];
- Optimization and uncertainty quantification for collaborative (federated) learning [e.g., FCP: Federated Conformal Predictors];
- Robustness under distribution shifts [e.g., ProjNorm: Predicting Out-of-Distribution Error].
Recent Publications [Google Scholar]
(*: equal contribution)White-Box Transformers via Sparse Rate Reduction.
Yaodong Yu, Sam Buchanan, Druv Pai, Tianzhe Chu, Ziyang Wu, Shengbang Tong, Benjamin D. Haeffele, Yi Ma.
In Proceedings of the 37th Conference on Advances in Neural Information Processing Systems (NeurIPS'2023), 2023. [arxiv] [code]
ViP: A Differentially Private Foundation Model for Computer Vision.
Yaodong Yu, Maziar Sanjabi, Yi Ma, Kamalika Chaudhuri, Chuan Guo.
Preliminary version presented at Theory and Practice of Differential Privacy Workshop (TPDP'2023), 2023. [arXiv] [code]
Federated Conformal Predictors for Distributed Uncertainty Quantification.
Charles Lu*, Yaodong Yu*, Sai Praneeth Karimireddy, Michael Jordan, Ramesh Raskar.
In Proceedings of the 40th International Conference on Machine Learning (ICML'2023), 2023. [link] [code]
Robust Calibration with Multi-domain Temperature Scaling.
Yaodong Yu, Stephen Bates, Yi Ma, Michael I. Jordan.
In Proceedings of the 36th Conference on Advances in Neural Information Processing Systems (NeurIPS'2022), 2022. [link]
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels.
Yaodong Yu, Alexander Wei, Sai Praneeth Karimireddy, Yi Ma, Michael I. Jordan.
In Proceedings of the 36th Conference on Advances in Neural Information Processing Systems (NeurIPS'2022), 2022. [link] [code]
Predicting Out-of-Distribution Error with the Projection Norm.
Yaodong Yu*, Zitong Yang*, Alexander Wei, Yi Ma, Jacob Steinhardt.
In Proc. of the 39th International Conference on Machine Learning (ICML'2022), 2022. [link] [code]
Professional Experiences
Visiting Researcher, FAIR at Meta, San Francisco, Oct. 2022 – Present
Research Intern, Meta AI, San Francisco, May. 2022 – Oct. 2022
Research Intern, Google Research, Remote, May. 2021 – Aug. 2021
Research Intern, Petuum, Pittsburgh, PA, May. 2018 – Dec. 2018
Research Assistant, School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore, Sep. 2016 – Aug. 2017