Grainger College of Engineering Seminars & Speakers

Abstract:    Gradient-based data attribution methods, such as influence functions, are critical for understanding the impact of individual training samples without repeated model retraining. However, their scalability is often limited by the high computational and memory costs associated with per-sample gradient computation, especially for large-scale models and datasets. In this talk, I will present our recent work on scalable influence function computation through sparse gradient compression and projection techniques with provable 
 guarantees. I will also discuss how these methods can be applied to real-world scenarios, such as online reinforcement learning where data filtering interacts with policy learning.
 
Bio:   Dr. Han Zhao is an Assistant Professor of Computer Science at the University of Illinois Urbana-Champaign (UIUC). Dr. Zhao earned his Ph.D. degree in machine learning from Carnegie Mellon University. His research interest is centered around trustworthy machine learning, with a focus on algorithmic fairness, robust generalization and data interpretability.