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—including first-order/zeroth-order stochastic algorithms, momentum-based methods, bi-level and min-max optimization, and equilibrium analysis for noncooperative games—and practical applications in LLM agents, alignment for large language models and diffusion models, robust machine learning, inverse reinforcement learning, differential privacy, and scalable fine-tuning algorithms.

Links: X (Twitter) 🤗 Hugging Face GitHub

Open Positions

We have research assistant and postdoctoral fellow positions available in the general areas of optimization, diffusion models, and LLM. If you are interested, please contact Dr. Hong.

Group News

  • Feb. 2026, paper accepted: Our tutorial paper Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design, joint work with Siliang, Luca, Chenliang, Jiaxiang, Volkan (EPFL), Stephano (Stanford), Markus (Google) and Alfredo (TAMU), has been accepted by SPM.

  • Jan. 2026, Sessions for INFORMS: M. and Jiaxiang are organizing three sessions on INFORMS Optimization Society Conference (IOS). Two sessions on optimization for foundations models, and one on bilevel optimization.

  • Dec. 2025, JPMorgan Chase Faculty Research Award: M. is awarded a JPMorgan Chase Faculty Research Award to support the research on the general direction of optimization for foundation models.

  • Sept. 2025, INFORMS Balas Prize: M. Receives the Egon Balas Prize from INFORMS Optimization Society. This prize is awarded annually to an individual for a body of contributions in the area of optimization.

  • July 2025, new grant: A new 3-year grant Collaborative Research: Unregistered Spectral Image Fusion in Remote Sensing: Foundations and Algorithms is awarded by NSF.

  • May 2025, new grant: A new 2-year grant Invariance in LLM Unlearning Advancing Optimization Foundations for Machine Unlearning is awarded by Open Philanthropy.

  • Jan. 2025, IEEE Fellow: M. is elected to IEEE Fellow with the citation “for contributions to optimization in signal processing, wireless communication and machine learning”.

  • Dec. 2022, SPS Best Paper Award: Our work Learning to optimize: Training deep neural networks for interference management (joint work with Haoran, Xiangyi, Qingjiang, Nikos and Xiao), published in IEEE TSP 2018, has been awarded the 2022 Signal Processing Society Best Paper Award.

See News for more updates.