Research archive

Publications.

First-order methods, structured optimization, and computational solvers.

View on Google Scholar

2026

Proceedings of the National Academy of Sciences (PNAS)

Large-scale semidefinite programming with graphics processing units

Qiushi Han, Zhenwei Lin, Hanwen Liu, Caihua Chen, Qi Deng, Dongdong Ge, and Yinyu Ye

Paper Project

Preprint

Global Linear Convergence of the Proximal Bundle Method under Unknown Piecewise Smoothness and Quadratic Growth

Zhenwei Lin and Zhe Zhang

Paper

Preprint

Accelerated Prox-Level Methods for Unknown Piecewise-Smooth Optimization II: Function-constrained Optimization

Zhenwei Lin and Zhe Zhang

Paper

INFORMS Journal on Computing / Accepted

Uniformly Optimal and Parameter-free First-order Methods for Convex and Function-constrained Optimization

Qi Deng, Guanghui Lan, and Zhenwei Lin

Paper

Preprint

Accelerated Prox-Level Methods for Unknown Piecewise-Smooth Optimization I: Convex Optimization

Zhenwei Lin and Zhe Zhang

Paper

2025

INFORMS Journal on Computing

A Low-Rank ADMM Splitting Approach for Semidefinite Programming

Qiushi Han, Chenxi Li, Zhenwei Lin, Caihua Chen, Qi Deng, Dongdong Ge, Huikang Liu, and Yinyu Ye

Paper Code

Preprint

A Practical GPU-Enhanced Matrix-Free Primal-Dual Method for Large-Scale Conic Programs

Zhenwei Lin, Zikai Xiong, Dongdong Ge, and Yinyu Ye

Paper Code

2024

NeurIPS

Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints

Zhenwei Lin and Qi Deng

Paper

ICML

A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes

Zhenwei Lin, Chenyu Xue, Qi Deng, and Yinyu Ye

Paper

AAAI

Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization

Zhenwei Lin, Jingfan Xia, Qi Deng, and Luo Luo

Paper