Revenue Management (Choice Model, Dynamic Pricing)
Data-driven optimization
Online Learning
Statistical Machine Learning
My research interest lies in data-driven decision-making and statistical learning. I aim to bridge between OR/MS and AI to increase reliability and interpretability for better managerial decisions. From the application prospective, I am interested in revenue management and pricing such as choice models.
* Full manuscript available by request.
Reproducing Kernel Hilbert Space (RKHS) Choice Model. [ssrn] with Yiqi Yang, Rui Gao, Shuang Li
Accepted at The Twenty-Sixth ACM Conference on Economics and Computation (EC'25) [Extended Abstract]
Acceptance rate: 202/927, 21.8%
A longer version in preparation to submit to journal
Neural-Network Mixed Logit Choice Model: Statistical and Optimality Guarantees. [ssrn] [poster] with Rui Gao and Shuang Li
Major Revision at Management Science
Second Place for Best Student Paper Competition at 15th POMS-HK Conference, (2nd out of 87 submissions)
Awarded UT Dissertation Writing Fellowship, McCombs PhD Conference
Deep Contextual-dependent Choice Model. [short version] with Shuhan Zhang, Rui Gao, and Shuang Li
Accepted as a spotlight paper at NeurIPS 2025 (acceptance rate: 3.2%)
Short version accepted as oral paper at 2nd Workshop on Models of Human Feedback for AI Alignment (MoFA), ICML 2025. (10% acceptance rate)
Improved Convergence Rate of Noisy Stochastic Gradient Descent for Interacting Langevin Dynamics.* with Rui Gao, Shuang Li
Working Paper
An Efficient UCB Algorithm for Contextual Learning with Continuous Actions.* [code] with Rui Gao
Working paper
Best presentation award with Charnes Fellowship, IROM Research Spring Symposium 2023, Austin
Reproducing Kernel Hilbert Space (RKHS) Choice Model.
INFORMS International 2025, Singapore
Neural-Network Mixed Logit Choice Model: Statistical and Optimality Guarantees.
INFORMS 2023, Phoenix
McCombs PhD Conference, Austin
Awarded UT Dissertation Writing Fellowship
MSOM 2024, Minneapolis
RMP 2024, Los Angeles
Analytics for X 2024, Singapore
INFORMS 2024, Seattle
Rotman Young Scholar Seminar Series (Virtually), Toronto
POMS-HK 2025, Hong Kong
Purdue Operations Conference, West Lafayette
Improved Convergence Rate of Noisy Stochastic Gradient Descent for Interacting Langevin Dynamics.
INFORMS International 2025, Singapore
An Efficient UCB Algorithm for Contextual Learning with Continuous Actions.
INFORMS 2022, Indianapolis
IROM Research Spring Symposium 2023, Austin
ICSP 2023, Davis
POMS-HK 2024, Hong Kong