Jiaming Liang

Jiaming Liang is an Assistant Professor in the Department of Computer Science and Data Science at the Hajim School of Engineering & Applied Sciences, University of Rochester. His research focuses on designing efficient algorithms for optimization and sampling in data science, with expertise in convex/nonconvex optimization, stochastic programming, and algorithmic game theory. He holds a PhD in Operations Research from Georgia Tech and completed a postdoctoral fellowship at Yale University under Andre Wibisono.

Education

• PhD in Operations Research, Georgia Institute of Technology
• Postdoctoral Researcher, Yale University (Yale CS Department)

Research Interests

Liang's work bridges theoretical optimization and practical algorithm design. He develops scalable methods for nonsmooth, stochastic, and high-dimensional problems, with applications in machine learning and data analysis. Key areas include:

• Proximal bundle methods for hybrid optimization
• Sampling algorithms under non-smooth conditions
• Accelerated gradient techniques
• Algorithmic game theory applications

Publications

His recent work emphasizes algorithmic unification (e.g., combining accelerated gradients with proximal bundle methods) and variance reduction strategies. He explores stochastic optimization without smoothness assumptions and develops sampling methods for nonconvex potentials.

Labs/Teams

While specific lab affiliations aren't detailed here, his research aligns with computational optimization and data science groups at the Hajim School.