Host
Co-Host
HKU IDS Seminar:
Learning Causal Representations
Abstract
Causal representations are models of real-world data that retain causal information, so in particular, they provide information about how a system will respond when subject to experimental intervention. While there is an extensive literature on how to discover the causal relations among a given set of variables, it is much less clear how to identify and construct the causal variables in the first place. Yet, given the vast amounts of measurement and sensor data available today, identifying the causal quantities has become just as important as identifying the relations between them. This presentation will focus on one approach, Causal Feature Learning, that learns a macro level causal representation from micro level measurement data. Time permitting, we will illustrate the method with applications in climate science, economics and neuroscience.
Speaker
Prof Frederick Eberhardt
Professor of Philosophy, California Institute of Technology
Frederick Eberhardt's research primarily focuses on methods for causation and how we might learn about causal relations from data. His research projects generally fall in an area of overlap between philosophy, machine learning, statistics, and cognitive science. He has also done some historical work on the philosopher Hans Reichenbach, especially on his frequentist interpretation of probability.
Before coming to Caltech in 2013, Eberhardt was an assistant professor in the Philosophy-Neuroscience-Psychology program in the department of philosophy at Washington University in St. Louis. He spent a year as a McDonnell Postdoctoral Fellow at the Institute of Cognitive and Brain Sciences at the University of California, Berkeley. He holds a PhD in Logic, Computation and Methodology from the department of philosophy at Carnegie Mellon University (CMU), and a masters in Knowledge Discovery and Data Mining from what is now CMU's Machine Learning Department.
For full biography of Prof. Eberhardt, please refer to: https://www.hss.caltech.edu/people/frederick-eberhardt#profile-399c3458-tab
Moderator
Prof Boris BABIC
Associate Professor, HKU IDS, Dept of Philosophy & Law(by courtesy), HKU Professor Boris Babic is HKU-100 Associate Professor at the University of Hong Kong, jointly appointed in the Musketeers Foundation Institute of Data Science, the Department of Philosophy, and (by courtesy) the Faculty of Law, from Fall 2023. He also serves as an occasional visiting professor in the Decision Sciences department at INSEAD. Professor Babic’s primary research interests are in Bayesian inference and decision-making, ethics, law, and policy of artificial intelligence and machine learning, especially in medical applications. His research has been published extensively in leading journals such as Science, Nature Machine Intelligence, Nature Digital Medicine, and the Harvard Business Review. For full biography of Prof. Babic, please refer to: https://datascience.hku.hk/people/boris-babic/
Moderator
Prof. Yi Ma
Director; Professor, Chair of Artificial Intelligence @ HKU IDS & Department of Computer Science
Professor Yi Ma is a Chair Professor in the Musketeers Foundation Institute of Data Science (HKU IDS) and Department of Computer Science at the University of Hong Kong. He took up the Directorship of HKU IDS on January 12, 2023. He is also a Professor at the Department of Electrical Engineering and Computer Sciences at the University of California, Berkeley. He has published about 60 journal papers, 120 conference papers, and three textbooks in computer vision, generalized principal component analysis, and high-dimensional data analysis.
Professor Ma’s research interests cover computer vision, high-dimensional data analysis, and intelligent systems. For full biography of Professor Ma, please refer to: https://datascience.hku.hk/people/yi-ma/
