Hi, welcome to my page! I am a Research Scientist at Meta. Prior to this, I was a postdoctoral associate at the Department of Electrical and Computer Engineering, University of Minnesota, mentored by Prof. Mingyi Hong and Prof. Shuzhong Zhang. I obtained my Ph.D. degree in Applied Mathematics at the Department of Mathematics, UC Davis, advised by Prof. Krishna Balasubramanian and Prof. Shiqian Ma. Prior to this, I received my B.S. degree in Mathematics from Zhejiang University. My CV is here.

My research lies at the intersection of applied mathematics, optimization theory, and artificial intelligence, with a focus on developing principled algorithms that advance both theoretical foundations and practical applications in modern machine learning. Specifically, I work on:

• Algorithm design for gradient-based, gradient-free (zeroth-order), and primal–dual methods for large-scale nonconvex optimization, including problems on Riemannian manifolds.
• Convergence theory for deterministic and stochastic minimax and bilevel optimization, with applications to machine learning and operations research.
• Distributed, decentralized and federated optimization algorithms for training large-scale AI systems.
• Theoretical foundations of reinforcement learning, especially policy-based methods, and their role in aligning large language models (LLMs).
• Efficient pre-training and fine-tuning methods for LLMs, bridging optimization principles with practical deployment.

News