About Me

I recently received my Ph.D. from the Department of Computer & Information Science & Engineering (CISE) at the University of Florida, where I was advised by Prof. Kejun Huang. Before joining UF, I obtained my bachelor’s degree from Nanjing University.

My research interests lie in the theoretical and algorithmic aspects of machine learning, with a particular focus on unsupervised learning, latent variable models, and non-convex optimization.

Specifically, my research includes:

• Identifiability of latent variable models, which enables principled pattern discovery in unsupervised learning, including nonnegative matrix factorization, bounded and independent component analysis, and dictionary learning.

• Efficient non-convex optimization algorithms with provable guarantees for structured learning problems.

• Applications of the above methods to machine learning, recommendation systems, natural language processing, and computer vision.

I am currently working on uncertainty-aware (e.g., bandit-based) recommendation systems for e-commerce and routing problems in multi-agent systems. I am also interested in extending the theoretical understanding of linear representation learning to modern large-scale deep neural networks, including large language models.

Research Keywords
Machine Learning, Representation Learning, Unsupervised Learning, Optimization, Latent Variable Models, Non-convex Optimization, Large Language Models, Foundation Models, Uncertainty Estimation, Recommendation Systems.

Publications
See my Google Scholar profile.

Selected Publications

• Complex Bounded Component Analysis: Identifiability and Algorithm. ICASSP 2024

• Global Identifiability of L1-based Dictionary Learning via Matrix Volume Optimization. NeurIPS 2023

• Identifiable Bounded Component Analysis via Minimum Volume Enclosing Parallelotope. ICASSP 2023