HKU IDS Scholar Seminar Series #23:
A Tangram Theory of Generalization: Rethinking Machine Learning via the Lens of Composition
Abstract
Modern machine learning models display abilities that exceed the assumptions of classical statistical learning, particularly their capacity to solve test‑time tasks far beyond those seen during training—an ability widely viewed as central to progress toward AGI. Such phenomena call for new theoretical frameworks. This talk presents a perspective based on composition: the idea that models generalize by recombining learned skills to address novel, more complex tasks. I will discuss empirical evidence and preliminary theoretical results supporting this viewpoint, aiming to motivate further investigation into this “tangram theory” of generalization.
Speaker
Prof Yingyu LIANG
Associate Professor @ HKU IDS & SCDS Professor Yingyu Liang is an Associate Professor in the Musketeers Foundation Institute of Data Science and Department of Computer Science at The University of Hong Kong. He is also an Associate Professor at the Department of Computer Sciences at the University of Wisconsin-Madison. Before that, he was a postdoc at Princeton University. He received his Ph.D. in 2014 from Georgia Tech, and M.S. (2010) and B.S. (2008) from Tsinghua University. He is a recipient of the NSF CAREER award. His research group aims at providing theoretical foundations for modern machine learning models and designing efficient algorithms for real world applications. Recent focuses include optimization and generalization in deep learning, robust machine learning, and their applications. For full biography of Prof. LIANG, please refer to: https://datascience.hku.hk/people/yingyu-liang/
Moderator
Prof Andrew Luo
Assistant Professor @ HKU IDS & PSYC Professor Andrew Luo is an Assistant Professor at the HKU Musketeers Foundation Institute of Data Science (IDS) and the Department of Psychology, The University of Hong Kong. He received his PhD in Neural Computation & Machine Learning from Carnegie Mellon University (advised by Prof. Michael J. Tarr and Prof. Leila Wehbe) and his BSc in Computer Science from MIT. His research sits at the intersection of computer vision, human visual representations, scene learning, and generative models, with a focus on building machine learning systems that perceive and understand the world in human-like ways, bridging cognitive science and AI. For full biography of Prof. Luo, please refer to: https://datascience.hku.hk/people/andrew-luo/
