Research

Research Directions

My research interests are optimization problems arising in machine learning, operations research and other applications. I am working on the following topics:

• Computational complexities for gradient-based, gradient-free (zeroth-order) and primal-dual algorithms for solving nonconvex optimizations and optimization on Riemannian manifolds.
• Convergence theory for deterministic and stochastic minimax/bilevel problems with applications in operations research and machine learning.
• Distributed optimization algorithms, including decentralized and federated learning.
• Theories for reinforcement learning algorithms, especially for multi-armed bandits and convergence of policy-based methods, and their applications in large language model (LLM) alignments.

I am also interested in theory and computation for supervised and unsupervised learning in general.