Assistant Professor, Business Analytics

Online learning, Reinforcement Learning, Game Theory

Zhang, M. & Luo, H. Contextual Multinomial Logit Bandits with General Value Functions. In Proceedings of Conference on Neural Information Processing Systems 2024.

Zhang, M., Vuong, R. D., & Luo, H. No-Regret Learning for Fair Multi-Agent Social Welfare Optimization. In Proceedings of Conference on Neural Information Processing Systems 2024.

Zhang, M., Pattathil, S., Slivkins, A., & Lucier, B. Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics. In Proceedings of Conference on Learning Theory 2024.

Zhang, M., Zhang, Y., Luo, H., & Mineiro, P. Provably Efficient Interactive-Grounded Learning with Personalized Reward. In Proceedings of Conference on Neural Information Processing Systems 2024. Vancouver, Canada.

"No-Regret Learning for Fair Multi-Agent Social Welfare Optimization," Poster at Conference on Neural Information Processing Systems, Vancouver, Canada, December 2025.

"Provably Efficient Interactive-Grounded Learning with Personalized Reward," Poster at Conference on Neural Information Processing Systems, Vancouver, Canada, December 2025.

"New Challenges for (Contextual) Multi-Armed Bandits: Fairness Objectives, Indirect Feedback, and Beyond," Guest/Invited Speaker at University of Illinois Urbana-Champaign, Champaign, Illinois, February 2025.

"Contextual Multinomial Logit Bandits with General Value Functions," Poster at Advances in Neural Information Processing Systems, Vancouver, Canada, December 2024.

Visiting Assistant Professor, Business Analytics, University of Iowa, 2024