About me

I am currently a Postdoctoral Research Scientist in the Department of Industrial Engineering and Operations Research at Columbia University, supervised by Prof. Xunyu Zhou.

I will join the Department of Applied Mathematics and Statistics at Johns Hopkins University as Assistant Professor in July 2024.

I completed my Ph.D. in the Department of Mathematics at the University of Texas at Austin, under the supervision of Prof. Thaleia Zariphopoulou. My doctoral committee members include Profs. Rui Gao, Irene M. Gamba, Mihai Sirbu, and Stathis Tompaidis.

My research lies at the intersection of data-driven decision making under uncertainty, stochastic and robust optimization, and machine learning. Specifically,

• Data-driven Decision Making under Uncertainty with Side Information. I develop robust and computationally efficient methodology with strong performance guarantees for decision-making problems involving contextual data. My works generate real-world impact and have industrial applications in supply chain management, revenue management, and fair machine learning.
• Optimal Information Acquisition. I develop stochastic control models that explore the optimal way to acquire information dynamically, and make a trade-off between the costly information learning and the expected return of the decision, given the limited information. My works draw inspiration from important real-world applications, including mechanism design and robo-advising.

I received my bachelor degree in Mathematics and Applied Mathematics (Honors Program) at Xi’an Jiaotong University in China, where I was also a student of the Speical Class for the Gifted Young before my undergraduate study.

Research

Publications

1. Luhao Zhang, Jincheng Yang, Rui Gao. Optimal Robust Policy for Feature-Based Newsvendor (2022), Management Science, forthcoming.

2. Luhao Zhang, Mohsen Ghassemi, Ivan Brugere, Alan Mishle, Niccolo Dalmasso, Vamsi Potluru, Tucker Balch, Manuela Veloso. Conditional Demographic Parity Through Optimal Transport (2022), NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Privacy.

Preprints

3. Luhao Zhang, Jincheng Yang, Rui Gao. A Simple and General Duality Proof for Wasserstein Distributionally Robust Optimization (2022), under review for Operations Research.

4. Jincheng Yang*, Luhao Zhang*, Ningyuan Chen, Rui Gao, Ming Hu. Decision-making with Side Information: A Causal Transport Robust Approach (2022), to be submitted to Operations Research.

5. Renyuan Xu, Thaleia Zariphopoulou, Luhao Zhang. Decision Making with Learning and Opportunity to Reverse (2022), to be submitted to Operations Research.

Teaching & Services

Teaching

I am interesting in teaching a wide range of courses, including different topics in probability, statistics, and optimization. I have taught several topics as following:

• Introduction to Mathematical Statistics

• Applied Statistics (Python, R)

• Probability

• Numerical Analysis (C++, Matlab, Python)

• Calculus

• Differential Equations

Professional Services

• Mathematical Programming

• ACM International Conference on AI in Finance

• INFORMS 2021 invited session of Learning and Decision-making with Contextual Information

• INFORMS 2022 invited session of Data-driven Decision Making

Directed Reading Program

The Directed Reading Program is an RTG program that pairs undergraduate students with graduate student mentors to undertake independent projects in mathematics.

Mentee

• Sonali Singh, on the topic of Stochastic Calculus for Finance2020 Spring

• Wenxuan Jiang, on the topic of Stochastic Calculus for Finance2021 Fall

• Haoze Yan, on the topic of Lectures on Stochastic Programming2022 Spring, Fall

• Yuxiang Gao, on the topic of Elements of Statistical Learning2022 Spring

Industry Experience & Skills

Industry Experience

• AI Researcher (Intern), JPMorgan Chase, New York, NY 2022 Summer

  Developed an efficient algorithm to achieve conditional demographic parity using causal transport distance

  Preliminary result accepted by NeurIPS Workshop on Algorithmic Fairness through the Lens of Causality and Privacy

Programming Languages

I have been teaching the following languages and their applications in Numerical Analysis and Applied Statistics:

• Python (Pandas, NumPy, TensorFlow, Scikit-Learn, SciPy)

• Matlab

• C++

• R

Miscellaneous

Awards & Fundings

• Frank Gerth III Teaching Excellence Award, UT Austin 2021

• Graduate School Summer 2021 Fellowship, UT Austin 2021