About me

I am a PhD Candidate in Industrial Engineering at the University of Wisconsin-Madison, under the guidance of Prof. Stephen Wright. I also hold an M.S. in Computer Science from the University of Wisconsin-Madison. Prior to my time in Madison, I earned a B.S. in Mathematics from the University of Science and Technology of China (USTC).

My research is centered on the design and analysis of optimization algorithms for machine learning applications.

I am actively seeking machine learning engineer/scientist positions in the industry! You can view my CV here.

Contact

Email: [firstname].[lastname] [at] wisc.edu

Publications

Changyu Gao, Andrew Lowy, Stephen J. Wright, Xingyu Zhou. Optimal Rates for Robust Stochastic Convex Optimization, Submitted.

Changyu Gao, Andrew Lowy, Stephen J. Wright, Xingyu Zhou. Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses. ICML 2024. [Poster Award, Midwest Machine Learning Symposium 2024] (link to paper)

Changyu Gao and Stephen J. Wright. Differentially Private Optimization for Smooth Nonconvex ERM arXiv preprint arXiv:2302.04972 (2023). [TPDP 2023 Poster]. (link to paper)

Charles Andrew Dickens, Changyu Gao, Connor Pryor, Stephen J. Wright, Lise Getoor. Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning. ICML 2024. (link to paper).

Dickens, Charles, Connor Pryor, Changyu Gao, Alon Albalak, Eriq Augustine, William Wang, Stephen Wright, and Lise Getoor. A mathematical framework, a taxonomy of modeling paradigms, and a suite of learning techniques for neural-symbolic systems, arXiv preprint arXiv:2407.09693 (2024). (link to paper)