Colloquium: "Causality and Learning"
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. On the other hand, we are also often concerned with how to do machine learning in complex environments, such as learning under data heterogeneity. For instance, how can we make optimal predictions in non-stationary environments? In the past decades, interesting advances were made in fields including machine learning, statistics, and philosophy for tackling long-standing causality problems, including how to discover causal knowledge from purely observational data and how to infer the effect of interventions using such data. Furthermore, 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 essential concepts in causality studies and is focused on how to learn causal relations from observation data and why and how the causal perspective helps in machine learning and other tasks.
Host: Nan Lin
Tea will be served @ 3:30 in room 200.