Speaker |
Fanghui Liu |
|---|---|
Affiliation |
University of Warwick |
Date |
Wednesday, 26 November 2025 |
Time |
12:30-13:30 |
Location |
Ground floor lecture theatre, Sainsbury Wellcome Center, 25 Howland St, W1T 4JG |
Link |
https://ucl.zoom.us/j/99748820264 |
Event series |
Jump Trading/ELLIS CSML Seminar Series |
Abstract |
In this talk, I will discuss some fundamental questions in modern machine learning: 1. What is a suitable model capacity of a modern machine learning model? 2. How to precisely characterize the test risk under such a model capacity? 3. What is the corresponding function space induced by such a model capacity? 4. What are the fundamental limits of statistical/computational learning efficiency within space? \ My talk will partly answer the above questions, through the lens of norm-based capacity control. By deterministic equivalence, we provide a precise characterization of how the estimator’s norm concentrates and how it governs the associated test risk. Our results show that the predicted learning curve admits a phase transition from under- to over-parameterization, but no double descent behavior, and reshapes scaling laws as well. Additionally, I will talk about the path-norm based capacities and the induced Barron spaces to understand the fundamental limits of statistical efficiency, particularly in terms of sample complexity and dimension dependence—highlighting key statistical-computational gaps. \ Talk based on https://arxiv.org/abs/2502.01585, https://arxiv.org/abs/2404.18769 |
Biography |
Dr. Fanghui Liu is currently an assistant professor at University of Warwick, UK, a member of Centre for Discrete Mathematics and its Applications (DIMAP), and a TUM Gloal Visiting professor. His research interests include foundations of machine learning as well as efficient machine learning algorithm design. He was a recipient of AAAI'24 New Faculty Award, Rising Star in AI (KAUST 2023), co-founded the fine-tuning workshop at NeurIPS'24, and served as an area chair of NeurIPS, ICLR and AISTATS, etc. Besides, he has delivered three tutorials at ISIT’24, CVPR’23, and ICASSP’23, respectively. Prior to his current position, he worked as a postdoc researcher at EPFL (2021-2023) and KU Leuven (2019-2023), respectively. He received his PhD degree from Shanghai Jiao Tong University in 2019 with several Excellent Doctoral Dissertation Awards. |