Machine learning has witnessed remarkable breakthroughs in recent years. Many machine learning techniques assume that the training and test data are sampled from an underlying distribution and aim to find a predictor with low population loss. However, in the real world, data may be generated by strategic individuals, collected by self-interested data collectors, possibly poisoned by adversarial attackers, and used to create predictors, models, and policies satisfying multiple objectives. As a result, predictors may underperform. To ensure the success of machine learning, it is crucial to develop trustworthy algorithms capable of handling these factors. In this talk, I will focus on how to deal with strategic individuals. The talk will be based on two recent works:

Han Shao, Avrim Blum and Omar Montasser. Strategic Classification under Unknown Personalized Manipulation. NeurIPS, 2023.

Lee Cohen, Yishay Mansour, Shay Moran, and Han Shao. Learnability Gaps of Strategic Classification. arXiv, 2024.

Han Shao is a fifth-year Ph.D. student at Toyota Technological Institute at Chicago (TTIC), advised by Prof. Avrim Blum. Her research focuses on theoretical foundations of machine learning, with a specific focus on fundamental questions arising from human social and adversarial behaviors in the learning process. She is interested in understanding how these behaviors affect machine learning systems and developing methods to enhance accuracy/robustness. Additionally, she is interested in gaining a theoretical understanding of empirical observations concerning adversarial robustness. Her papers have been published at machine learning venues including NeurIPS, ICML, COLT, etc. She was awarded EECS Rising Star by Georgia Tech and Rising Star in Machine Learning by the University of Maryland in 2023. She will be joining the Department of Computer Science at the University of Maryland in Fall 2025 as an Assistant