Doctoral Student in Management Science
School of Management, Fudan University
Visiting Scholar, Georgia Tech ISyE (2025–2026)
Email: 23110690009@m.fudan.edu.cn
Google Scholar: Mingjie Hu
I am a fourth-year Ph.D. student in Management Science at the School of Management, Fudan University, advised by Professor Jian-Qiang Hu. From 2025 to 2026, I was a Visiting Scholar at the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech, where I worked with Professor Enlu Zhou. I also collaborate with Professor Chun-Hung Chen and Professor Jie Xu at George Mason University, and with Professor Siyang Gao at City University of Hong Kong. I received my bachelor's degree in Information Management and Information Systems from Central South University in 2021.
I am currently on the academic job market.
My research interests include adaptive experiment design, quantum computing, and agent-based simulation.
I study how to collect data efficiently when observations are costly and the system is only partly known. My work develops adaptive methods for best-arm identification, reinforcement learning, LLM policy optimization, and operational experiments, with the goal of learning the information most relevant to the final decision.
I study how quantum computing can improve stochastic optimization and simulation. My work characterizes the performance limits of quantum algorithms for discrete simulation optimization and develops algorithms that attain those limits.
My interests include calibrating LLM-based agents with real data, quantifying uncertainty in their outputs, and using them for decision-making under uncertainty.
Numerical results · Table 1
Quantum nested estimation and plurality voting select an alternative under a fixed query budget.
Expected optimality gap · Figure 1
QUEST combines quantum estimation and sequential elimination to approach the optimal expected decision error under a fixed budget.
Query complexity · Figure 1
Quantum value estimation and tree elimination identify a near-optimal move with a prescribed confidence level.
Oracle queries · Figure 5
Grover search and adaptive thresholds identify near-optimal simulation decisions with a prescribed confidence level.
Empirical query complexity · Figure 1
Quantum sequential elimination identifies the best feasible alternative under stochastic constraints.
Email: 23110690009@m.fudan.edu.cn