Jiaming Liang (梁家銘)

Jiaming Liang [Google Scholar] Assistant Professor Goergen Institute for Data Science & Department of Computer Science University of Rochester Office: Wegmans Hall 2403, 250 Hutchison Rd, Rochester, NY 14620 Email: firstname DOT lastname AT rochester DOT edu

Short Bio

Jiaming is an assistant professor in Data Science and Computer Science at the University of Rochester. He was a postdoctoral researcher at Yale CS department, under the supervision of Andre Wibisono. He obtained Ph.D. in Operations Research at Georgia Tech, advised by Renato Monteiro.

Research Interests

His primary research goal is to design, analyze and implement fast algorithms for solving a general class of problems in data science. His research interests broadly include topics in optimization and sampling algorithms, such as

• Convex and Nonconvex Optimization

• Nonsmooth Optimization

• Stochastic Optimization

• Sampling Algorithms

News

• A new paper “Universal subgradient and proximal bundle methods for convex and strongly convex hybrid composite optimization”.

• A new paper “Proximal Oracles for Optimization and Sampling”.

• A new paper “On Independent Samples Along the Langevin Diffusion and the Unadjusted Langevin Algorithm”.

• A new paper “Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method”.

• The paper “A single cut proximal bundle method for stochastic convex composite optimization” has been published in Mathematical Programming.

• A new paper “Proximal bundle methods for hybrid weakly convex composite optimization problems”.