Causality and Learning¶
Kun Zhang
Assistant Professor
Carnegie Mellon University, USA
Abstract: Can we find the causal direction between two variables? How can we make optimal
predictions in the presence of distribution shift? We are often faced with such
causal modeling or prediction problems in various disciplines. Recently, with the
rapid accumulation of huge volumes of data, both causal discovery, i.e., learning
causal information from purely observational data, and machine learning are
seeing exciting opportunities as well as great challenges. This talk will be focused
on recent advances in causal discovery and how causal information facilitates
understanding and solving certain problems of learning from heterogeneous data.
In particular, I will talk about conditional independence-based and functional causal
model-based approaches to causal discovery, including their underlying
assumptions, algorithms, and applications. Practical issues in causal discovery,
including selection bias, nonstationarity or heterogeneity of the data, and high-dimensionality of the problem, will also be addressed. Finally, I will discuss why and
how underlying causal knowledge helps in learning from heterogeneous data when
the i.i.d. assumption is dropped, with transfer learning as a particular example.
Bio: Kun Zhang is an assistant professor in the philosophy department and the machine
learning department (affiliated) of Carnegie Mellon University (CMU), USA, and a
senior research scientist at Max Planck Institute for Intelligent Systems, Germany.
His main research interests include causal analysis, machine learning, artificial
intelligence, computational finance, and large-scale data analysis. He has made a
series of contributions in solving some long-standing problems in causality, such as
how to distinguish cause from effect and how to make nonparametric conditional
independence test reliable. He has served as a senior program committee member
or area chair for a number of conferences in machine learning or artificial
intelligence, and organized various academic activities to foster interdisciplinary
research in causality.