Quanquan Gu

Quanquan Gu is an Assistant Professor in the Department of Computer Science at the University of California, Los Angeles (UCLA). His research spans machine learning, privacy-preserving algorithms, and distributed optimization, with applications in public health modeling and data science.

• Affiliation: Department of Computer Science, UCLA
• Academic Rank: Assistant Professor

Gu's work addresses fundamental challenges in federated learning, non-convex optimization, and statistical learning. He has contributed to privacy-preserving methods like differentially private stochastic optimization and federated diffusion model training, while also exploring robustness in epidemic modeling under uncertainty.

His recent publications highlight trends in privacy-preserving machine learning, including adaptive client sampling in federated systems and secure distributed non-convex optimization. He has also published on epidemiological forecasting, notably analyzing limitations in nationwide disease prediction models during the 2020-2021 pandemic period.

• Current advisees: 7 PhD students (including Yuan Cao, Jinghui Chen, Difan Zou) and 4 Master's students (Felicia Gao, Arjun Srinivasan)
• Alumni: 1 PhD graduate (Shi Pu) and 15 Master's graduates (including Xiao Zhang, Yaodong Yu, James Xie)

Gu's teaching and research emphasize practical implementation of theoretical algorithms, with a focus on communication-efficient distributed learning and robust statistical estimation in high-dimensional settings.