Learning Causality and Learning with Causality: A Road to Intelligence
Time: 2019-11-28
Published By: Li Yang
Speaker(s): Kun Zhang (CMU)
Time: 12:00-13:30 December 5, 2019
Venue: Room 9, Quan Zhai, BICMR
Abstract: Does smoking cause cancer? Can we find the causal direction between two variables by analyzing their observed values? In our daily life and science, people often attempt to answer such causal questions, for the purpose of understanding and manipulating systems properly. In the past decades, interesting advances were made in fields including machine learning, statistics, and philosophy in order to answer such questions. Furthermore, we are also often concerned with how to do machine learning in complex environments. For instance, how can we make optimal predictions in non-stationary environments? How can we achieve the so-called general-purpose AI? Interestingly, it has recently been shown that causal information can facilitate understanding and solving various machine learning problems, including transfer learning and semi-supervised learning. This talk reviews focused on how to learn causal relations from observation data in light of different types of independence, why and how the causal perspective helps in learning under data heterogeneity, and the connection between artificial intelligence and the causal view.
Bio: Kun Zhang is an assistant professor in the philosophy department and an affiliate faculty member in the machine learning department at Carnegie Mellon University, and a senior research scientist at Max Planck Institute for Intelligent Systems, Germany. His research interests lie in machine learning and artificial intelligence, especially in causal discovery, causality-based learning, and general-purpose artificial intelligence. He develops methods for automated causal discovery from various kinds of data, investigate learning problems, especially transfer learning, concept learning, and deep learning, from a causal view, and study philosophical foundations of causation and various machine learning tasks. He coauthors a best student paper for UAI and received the best benchmark award of the causality challenge, and has served as an associate editor for three international journals and an area chair or senior program committee member for major conferences in machine learning or artificial intelligence, including NeurIPS, UAI, ICML, AISTATS, AAAI, and IJCAI. He has organized various academic activities to foster interdisciplinary research in causality.
Noted:This is the lunchtime talk，we would like to service some slight food. Due to objective conditions, the quota for this luncheon meeting is 20 on a first-come-first-served basis.
