Research

($\star$ stands for the corresponding author(s), $\dagger$ stands for equal contribution.)

1. Journal Papers Published/Accepted

1. An Enhanced Alternating Direction Method of Multipliers-Based Interior Point Methods for Linear and Conic Optimization

   • ($\alpha$-$\beta$) Qi Deng, Qing Feng, Wenzhi Gao, Dongdong Ge, Bo Jiang$^{\star}$, Yuntian Jiang, Jinsong Liu, Tianhao Liu, Chenyu Xue, Yinyu Ye, Chuwen Zhang

   • INFORMS Journal on Computing (IJoC), 2024

1. A Homogeneous Second-Order Descent Method for Nonconvex Optimization

   • Chuwen Zhang, Chang He, Yuntian Jiang, Chenyu Xue$^{\star}$, Bo Jiang$^{\star}$, Dongdong Ge, Yinyu Ye

   • Mathematics of Operations Research (MOR), 2025

1. Assortment Optimization in the Presence of Focal Effect: Operational Insights and Efficient Algorithms

   • ($\alpha$-$\beta$) Bo Jiang, Zizhuo Wang, Chenyu Xue$^{\star}$, Nanxi Zhang$^{\star}$

   • Production and Operations Management (POM), 2025

   • An extended abstract appears at the 19th Conference on Web and Internet Economics (WINE 2023)

1. Beyond $O(\sqrt{T})$ Regret: Decoupling Learning and Decision-making in Online Linear Programming

   • ($\alpha$-$\beta$) Wenzhi Gao, Dongdong Ge$^{\star}$, Chunlin Sun, Chenyu Xue$^{\star}$, Yinyu Ye

   • Operations Research (OR), 2026

   • An earlier version appears at the 41st International Conference on Machine Learning, titled by Decoupling Learning and Decision-Making: Breaking the barrier in Online Resource Allocation with First-Order Methods

2. Papers Under Revision/Review

1. Robust Pricing with Randomization: A Multi-Criteria Perspective

   • ($\alpha$-$\beta$) Mingyang Fu, Hongyuan Lin$^{\star}$, Chenyu Xue

   • Under Review at Operations Research (OR), 2026

   • Best Paper Award (Third Prize), CSAMSE International Annual Conference 2026

3. Papers in Progress

1. On the Expressiveness and Tractability of Mixture Choice Models

   • with Zhejun Xi and Bo Jiang

1. Online Assortment Optimization under the Marginal Exponential Model

   • with Bo Jiang, Xiaobo Li and Shuzhong Zhang

4. Papers in Conference Proceedings

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

   • Zhenwei Lin$^{\dagger}$, Chenyu Xue$^{\dagger}$, Qi Deng$^{\star}$, Yinyu Ye

   • Proceedings of the 41st International Conference on Machine Learning (ICML 2024)

1. A Homogenization Approach for Gradient-Dominated Stochastic Optimization

   • Jiyuan Tan$^{\dagger}$, Chenyu Xue$^{\dagger, \star}$, Chuwen Zhang, Qi Deng, Dongdong Ge, Yinyu Ye

   • Proceedings of the 40th Conference on Uncertainty in Artificial Intelligence (UAI 2024)