About The Event
Developing realistic models of human intelligence and learning is a major aspiration of several scholarly fields, including Artificial Intelligence, Economics, and Philosophy. The ability to conceptualize causal structure in the external world and to use causal representations to guide behavior is an essential feature of human intelligence. Indeed, causality is now the mainstream focus within a heterogeneous set of scientific circles. A review of prestigious research awards is one indicator of the breadth and depth of interest in the study of causal systems. For instance, in Computer Science, the 2011 Turing Award went to Judea Pearl for “the development of a calculus for causal reasoning.” In Economics, the 2021 Nobel Prize went to David Card, Guido Imbens, and Joshua Angrist for “advances in causal inference in economic settings.” In Machine Learning, there is a growing recognition that the path to building artificial agents that exhibit truly human-like intelligence runs through causal reasoning. For example, Yoshua Bengio, himself a recent winner of the Turing Award for his work in Deep Learning, says: "We don't have AI systems which actually understand at the level that humans do or anywhere close. What does understanding mean? ... In part it means capturing the causal structure in the world."
The goal of this workshop is to stimulate fruitful conversations about causal learning among a diverse community of world-class researchers. The recent burst of interdisciplinary research on causality and machine learning clearly shows the potential for mutual benefit through idea-sharing and integration. Here, we aim to bring two additional disciplines into the conversation: the first is game theory, which has much to say about interactive decision making, as well as having an extensive line of work exploring a broad range of human learning dynamics. The second is philosophy, which has much to say about human conceptualization, certain lines of which are particularly relevant to interactive causal learning. We are casting a wide net to draw in a broad range of cutting-edge perspectives - be it work investigating specific aspects of causality per se, or cutting-edge work that may not be directly about causality but, nevertheless, holds promise to benefit our effort.
This event begins with a series of virtual Keynotes designed to provide state-of-play overviews of each of the following fields: machine learning, causality, game theory, and philosophy. These will be then followed by a two-day, in-person, workshop in Washington D.C. The invited papers will all provide exciting contributions in these related disciplines. We also aim to spark interdisciplinary discussions and research. To that end, time has been set aside during the conference for socializing and informal conversations between participants.
Virtual Keynotes
Because this conference is designed to share ideas across disciplines and because cross-disciplinary communication is non-trivial, we have organized four pre-conference keynotes. We are honored to have four world-class scholars, each of whom will give an overview of the key research issues, findings, and methods of their respective areas. The idea is that these keynotes will provide something of a "Rosetta Stone" to meeting participants to facilitate interdisciplinary exchange during the actual meeting. These talks are open to the public, with registration information and webinar recordings provided at the links to each talk below.

Richard Zemel
Columbia University

Drew Fudenberg
MIT

Rani Lill Anjum
Norwegian University

Elias Bareinboim
Columbia University
Speakers
Speaker details and recorded presentations are available through the links below

Michel Besserve
Max Planck Institute

Fabrizio Cariani
University of Maryland

Brian Epstein
Tufts University

Albin Erlanson
University of Essex

Nicola Gatti
Politecnico di Milano

Thomas Icard
Standford University

Rosemary Ke
Deepmind

Konrad Kording
University of Pennsylvania

Lihua Lei
Stanford University

Marco Lin
UCL

Judith Lok
Boston University

James Madden
Benedictine College

Sara Magliacane
University of Amsterdam

Sarah Paul
New York University Abu Dhabi

Emilija Perković
University of Washington

Peter Spirtes
Carnegie Mellon University

Burkhard Schipper
University of California, Davis

Chandler Squires
MIT

Vasilis Syrgkanis
Microsoft Research, New England

Mark van der Laan
University of California, Berkeley

Jeremy Wilkins
Boston College
First International Workshop on
Interactive Causal Learning
2022 Conference Agenda
Welcome Cocktail Reception and Dinner
Breakfast
Introductory Comments
Reality and Our Ability to Explain It
Going Behind the Back of Consciousness: The Pre-Cognitive Contact with Reality and Learning to Operate in the Space of Reasons
Causality’s Shadow in Language
Break
From Causal Insights to Deeper Learning
Lunch
Machine Learning and Estimation 1
Higher Order Targeted Maximum Likelihood Estimation
Automatic Debiased Machine Learning with Generic Machine Learning for Static and Dynamic Causal Parameters
Conformal Inference of Counterfactuals and Individual Treatment Effects
Break
Learning in Socio-Economic Settings
Predicting the Unpredictable under Subjective Expected Utility
Optimal Allocations with Capacity Constrained Verification
Safe Learning in Tree-Form Sequential Decision Making: Handling Hard and Soft Constraints
Free Time
The National Building Museum
Buses Depart from the Westin Georgetown
Access to the Notre Dame de Paris Exhibition
Dinner in the Pension Commisioner's Suite
Buses Return to the Wastin Georgetown
Breakfast
Grasping Consequences; From Individual to Social
Who’s Asking? Insight and the Problem of Getting Questions Right
Causation and the Nature of the Social World
Break
Machine Learning and Estimation 2
Omitted Variable Bias in Machine Learned Causal Models
Causal Organic Indirect and Direct Effects: Closer to Baron and Kenny, and Related to Surrogate Outcomes
From What to Why: Towards Causal Deep Learning
Lunch
Causal Discovery and Identification 1
Total Causal Effect in MPDAGs: Identification and Minimal Enumeration
The Query Complexity of Verifying a Causal Graph from Single-Node Interventions
Machine Learning and Learning Causality from Observational Data
Break
Causal Discovery and Identification 2
Causality-Inspired ML: How Can Causality Help ML?
Learning from Causal Explanations
Panel: Interdisciplinary Insights and Next Steps
Brian Epstein
Burkhard Schipper
Rosemary Ke
Ting Ye
Zachary Lipton
Conference Ends
Workshop Organizers

Michael D. Ryall
University of Toronto

Carlos Cinelli
University of Washington

Nadia Al-Banna
University of Toronto

Daniel Simmonds
Queen's University
Event Venue
Event venue location info and gallery