Research Overview

Bridging AI and Optimization

Developing cutting-edge algorithms at the intersection of machine learning and mathematical optimization to solve large-scale decision-making problems.

2 Research Areas
2+ Publications

Research Topics

Click on a topic to explore related publications and projects

AI for Optimization

Using machine learning to learn powerful heuristics for combinatorial optimization problems

ICLR 2026

FMIP: Joint Continuous-Integer Flow for Mixed-Integer Linear Programming

Hongpei Li, Hui Yuan, Han Zhang, Jianghao Lin, Dongdong Ge, Mengdi Wang, Yinyu Ye

The first generative framework that models the joint distribution of both integer and continuous variables for MILP solutions. Achieves 41.34% improvement over existing baselines with holistic guidance mechanism.

Flow Matching Generative Models MILP 41.34% Improvement

Large-Scale Optimization

Scaling primal-dual algorithms to distributed multi-GPU architectures

arXiv

D-PDLP: Scaling PDLP to Distributed Multi-GPU Systems

Hongpei Li, Yicheng Huang, Huikang Liu, Dongdong Ge, Yinyu Ye

The first distributed PDHG-based solver for large-scale LPs that scales across multiple GPUs. Achieves near-linear speedup with up to 6× faster solving on 8 GPUs while maintaining full FP64 numerical accuracy.

PDHG Multi-GPU Distributed 6× Speedup

All Papers

Paper Venue Topic Key Result Links
FMIP Joint Continuous-Integer Flow for MILP ICLR 2026 AI for Opt 41.34% improvement
D-PDLP Scaling PDLP to Distributed Multi-GPU arXiv Large-Scale 6× speedup on 8 GPUs