Hongpei Li ☕️
Hongpei Li

Large-Scale Optimization

Download CV

About Me

I will join the Department of Industrial Engineering & Management Sciences (IEMS) at Northwestern University as a PhD student in Fall 2026.

I received my Bachelor’s degree from Shanghai University of Finance and Economics (2021.9 - 2025.6), in the Pilot Class of Interdisciplinary Sciences.

📚 My Research

My research interests include Optimization, Artificial Intelligence (AI), and the interdisciplinary area between Operations Research and Machine Learning.

Currently, I am particularly focused on:

  • Developing optimization-based algorithmic frameworks to enhance the training and inference efficiency of large language models (LLMs)
  • Accelerating classical optimization methods by leveraging AI techniques that learn from historical data
  • Designing and implementing efficient optimization algorithms for large-scale problems, with a particular focus on GPU-accelerated methods
Recent Publications
(2026). OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention. arXiv.
(2026). PDHCG-II: An Enhanced Version of PDHCG for Large-Scale Convex QP. arXiv.
(2026). D-PDLP: Scaling PDLP to Distributed Multi-GPU Systems. arXiv.
(2025). BenLOC: A Benchmark for Learning to Configure MIP Optimizers. arXiv.
(2025). PDHCG: A Scalable First-Order Method for Large-Scale Competitive Market Equilibrium Computation. arXiv.