OptimAI Lab

Electrical and Computer Engineering, University of Minnesota

Mingyi_Hong.png

6-109 Keller Hall

Minneapolis, MN 55455

TEL: (612)-625-3505

Email: mhong at umn.edu

The Optimization for Artificial Intelligence (OptimAI) Lab at the University of Minnesota focuses on designing and analyzing optimization methods for problems arising in data science, machine learning, and AI. Our research spans both theoretical foundations and practical applications.

Research Interests

Our research focuses on theoretical topics including:

  • Design and Analysis for first-order/zeroth-order, stochastic, convex and nonconvex algorithms
  • Design and Analysis for Momentum-Based Methods
  • Bi-level and Min-Max optimization problems
  • Analysis of equilibrium solutions for noncooperative games

These theoretical developments are empowered by applications in various engineering domains:

  • LLM Agents
  • Alignment for Large Language Models and Diffusion Models
  • Robust (Adversarial) Machine Learning
  • Inverse Reinforcement Learning and Structural Estimation
  • Differential Privacy
  • Scalable fine-tuning algorithms

news

May 10, 2025 Siliang Zeng successfully defended his thesis. Congratulations, Dr. Zeng!
Sep 15, 2024 Group Kayak Activity, with visiting student Chung You Yau from CUHK.
Dec 10, 2023 The group attended NeurIPS 2023.
Nov 25, 2023 Xinwei Zhang Graduation Dinner celebration.
Nov 20, 2023 Xinwei Zhang successfully defended his thesis. Congratulations, Dr. Zhang!
Sep 15, 2023 Group Kayak Activity.
Dec 15, 2022 Group Escape Room Activity.
Oct 15, 2022 Group Hiking Activity at Afton.
May 15, 2022 Xiangyi Chen graduated. Congratulations!
Jun 15, 2021 Our work entitled STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning has been made available online at arXiv. This paper designed a federated learning algorithm which achieves the optimal sample and communication complexity.

selected publications

  1. optimization.png
    A Unified Algorithmic Framework for Block-Structured Optimization Involving Big Data
    Mingyi Hong, Meisam Razaviyayn, Zhi-Quan Luo, and 1 more author
    IEEE Signal Processing Magazine, Jan 2016
    Abs DOI arXiv
  2. Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problems
    Mingyi Hong, Zhi-Quan Luo, and Meisam Razaviyayn
    SIAM Journal on Optimization, 2016
    ICCOPT Best Paper Finalist DOI arXiv
  3. A Unified Convergence Analysis of Block Successive Minimization Methods for Nonsmooth Optimization
    Meisam Razaviyayn, Mingyi Hong, and Zhi-Quan Luo
    SIAM Journal on Optimization, 2013
    ICCOPT Best Paper Finalist DOI arXiv
  4. Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
    Haoran Sun, Xiangyi Chen, Qingjiang Shi, and 3 more authors
    IEEE Transactions on Signal Processing, 2018
    DOI arXiv Code
  5. Block Alternating Optimization for Non-Convex Min-Max Problems: Algorithms and Applications in Signal Processing and Communications
    Songtao Lu, Ioannis Tsaknakis, Mingyi Hong, and 1 more author
    IEEE Transactions on Signal Processing, 2020
    DOI arXiv
  6. Non-Convex Min-Max Optimization: Applications, Challenges, and Recent Theoretical Advances
    Meisam Razaviyayn, Tianjiao Huang, Songtao Lu, and 3 more authors
    IEEE Signal Processing Magazine, 2020
    DOI arXiv