Room: El Veril

The past decades have seen a series of cross-disciplinary advances in causal discovery and causal inference. In particular, recently a number of long-standing problems, such as how to learn causal information from observations and how causal modeling and transfer learning benefit each other, have received much attention in philosophy, machine learning, and psychology. However, researchers may not be aware of the methodologies used and developments achieved in other fields. This workshop aims to provide a platform for people who study causality in machine learning, psychology, and neuroscience to share the state-of-the-art and perspectives in their respective disciplines, get inspiration from others, and foster interdisciplinary collaboration in the study of fundamental problems in causality.


  • Bernhard Schölkopf
  • David Danks
  • Tom Claassen
  • Michel Besserve
  • Fei Sha
  • Chris Lucas
  • Moritz Grosse-Wentrup
  • Björn Meder

09:30- 10:00 The principle of independent mechanisms Bernhard Schölkopf, Max Planck Institute for Intelligent Systems

10:00- 10:30 Causal discovery in psychometric data sets: the search for aggression and conduct disorders Tom Claassen, Radboud University Nijmegen

10:30- 11:00 Human causal learning via local inferences David Danks, Carnegie Mellon University

11:30- 12:00 Discovering and exploiting structure in the face of changing tasks Chris Lucas, University of Edinburgh

12:00- 12:30 Do we really have a shot at solving zero-shot learning for object recognition? Fei Sha, University of Southern California

12:30- 13:00 Distinguishing between the neural correlates and the neural basis of cognition Moritz Grosse-Wentrup, Max Planck Institute for Intelligent Systems

18:00- 18:30 Diagnostic causal reasoning with verbal uncertainty terms Björn Meder, Max Plank Institute for Human Development

18:30- 19:00 Causal inference from a group invariance perspective Michel Besserve, Max Planck Institute for Intelligent Systems