"Could it have been different?"

ICML Workshop on Counterfactuals
in Minds and Machines

July 29, 2023
Hawaii Convention Center, Room 301 + ZooM

The workshop is concluded. We thank all speakers and attendees for their participation! Recordings are available on the ICML website.


"Had I left 5 minutes earlier, I would have caught the bus."

"Had I been driving slower, I would have avoided the accident."

Counterfactual thoughts—“what if?” scenarios about outcomes contradicting what actually happened—play a key role in everyday human reasoning and decision-making. In conjunction with rapid advancements in the mathematical study of causality, there has been an increasing interest in the development of machine learning methods that support elements of counterfactual reasoning, i.e., they make predictions about outcomes that "could have been different". Such methods find applications in a wide variety of domains ranging from personalized healthcare and explainability to AI safety and offline reinforcement learning. Although the research at the intersection of causal inference and machine learning is blooming, there has been no venue so far explicitly focusing on methods involving counterfactuals. In this workshop, we aim to fill that space by facilitating interdisciplinary interactions that will shed light onto the three following questions: 

Invited Speakers

University of Dublin

University of California at Berkeley

Stanford University

Harvard University

University of Cambridge

Johns Hopkins University

Panel discussion

"Counterfactual reasoning: From minds to machines to practical applications”

Therein, our diverse set of speakers across computer science, cognitive psychology, and philosophy will discuss similarities and differences between humans and machines in counterfactual reasoning, as well as ways to make counterfactual-based methods more broadly adopted in relevant applications. Audience questions will be encouraged to make the discussions more interactive.


For questions, please contact us at counterfactuals.icml@gmail.com