PhD Dissertation Defense by SHAO Qian | Learning and Optimization under Human-Centric Considerations

Learning and Optimization under Human-Centric Considerations

ABOUT THE TALK

This dissertation investigates learning and optimization problems shaped by human-centric considerations, such as preferences, demonstrations, behavioral patterns, and resource constraints. As real-world decision-making increasingly involves interaction with human agents, data, and limitations, modeling these factors becomes critical for building practical, adaptive, and robust systems. 

The research spans four domains. First, we study preference-aware delivery routing by learning implicit practitioner preferences and incorporating them into a hierarchical route optimization framework. Second, we develop imitation learning methods for cost-constrained settings, enabling agents to mimic expert behavior while respecting safety and resource limitations. Third, we explore early rumor detection in data-limited environments, integrating large language models (LLMs) with imitation-learning agents to identify misinformation patterns driven by fallible human reasoning. Finally, we address constrained dynamic pricing problems using discrete choice models, proposing a tractable approximation method to ensure compliance with real-world pricing constraints. 

Together, these contributions demonstrate how human behavior—whether implicit or explicit—can be effectively integrated into learning and optimization frameworks. The thesis provides practical methodologies that bridge the gap between theoretical models and the complexities of human-influenced environments across logistics, robotics, economics, and social media analysis.

SPEAKER BIOGRAPHY

SHAO Qian is a Ph.D. candidate in Computer Science at the SMU SCIS, supervised by Prof. CHENG Shih-Fen. Her research interests are last-mile logistics, imitation learning and approximate dynamic programming.