Causal inference is one of the main areas of focus in artificial intelligence (AI) and machine learning (ML) communities. Causality has received significant interest in ML in the recent years in part due to its utility for generalization and robustness. It is also central for tackling decision-making problems such as reinforcement learning, policy or experimental design. Information-theoretic approaches provide a novel set of tools that can expand the scope of classical approaches to causal inference and discovery problems in a variety of applications. Some examples of the success of information theory in causal inference are: the use of directed information, minimum entropy couplings and common entropy for bivariate causal discovery; the use of the information bottleneck principle with applications in the generalization of machine learning models; analyzing causal structures of deep neural networks with information theory; among others.
The goal of ITCI’22 is to bring together researchers working at the intersection of information theory, causal inference and machine learning in order to foster new collaborations and provide a venue to brainstorm new ideas, exemplify to the information theory community causal inference and discovery as an application area and highlight important technical challenges motivated by practical ML problems, draw the attention of the wider machine learning community to the problems at the intersection of causal inference and information theory, demonstrate to the community the utility of information-theoretic tools to tackle causal ML problems
Topics include but are not limited to
• Novel algorithmic solutions to causal inference or discovery problems using information-theoretic tools or assumptions.
• Applications of causal inference in machine learning/deep learning motivated by information-theoretic approaches (e.g. information bottleneck principle)
• Characterization of fundamental limits of causal quantities using information theory.
• Identification of information-theoretic quantities relevant for causal inference and discovery.
ITCI’22 will be a one-day workshop. The program consists of invited and spotlight talks, and socials for one-on-one discussions. Attendance is open to all; at least one author of each accepted paper must be virtually present at the workshop.
Submissions of technical papers can be up to 7 pages excluding references and appendices. Short or position papers of up to 4 pages are also welcome. All papers must be submitted in PDF format, using the AAAI-22 author kit and anonymized. Papers will be peer-reviewed and selected for spotlight and/or poster presentation at the workshop.
Submission site: https://cmt3.research.microsoft.com/ITCI2022
November 12, 2021. November 26, 2021 AoE.
Notification to Authors:
December 3, 2021. December 7, 2021.
Camera-ready/Slides Due: February 18. 2022 AoE.
Mihaela van der Schaar
Christopher J. Quinn
Mihaela van der Schaar is the John Humphrey Plummer Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge, a Fellow at The Alan Turing Institute in London, and a Chancellor’s Professor at UCLA. Mihaela’s research focus is on ML, AI and OR for healthcare and medicine.
Nihat Ay is a professor at the Hamburg University of Technology, leading the Institute for Data Science Foundations. As a part-time professor of the Santa Fe Institute, he is involved in research on complexity and robustness theory. He has co-authored a book and written numerous articles on this subject. Furthermore, he serves as the Editor-in-Chief of the Springer journal Information Geometry.
Volker Roth is a professor in the Department of Mathematics and Computer Science at the University of Basel. His research interests include machine learning, statistical models for data analysis and biomedical applications.
Christopher J. Quinn is an assistant professor in the Department of Computer Science at Iowa State University. He is broadly interested in machine learning, information theory, and network science with applications in neuroscience and social networks.
Spotlight Presentations 1
9:30am - 9:45am:
Formally Justifying MDL-based Inference of Cause and Effect
Alexander Marx, Jilles Vreeken
9:45am - 10:00am:
Quantifying Feature Contributions to Overall Disparity Using Information Theory
Sanghamitra Dutta, Praveen Venkatesh, Pulkit Grover
10:00am - 10:15am:
Causal Inference with Heteroscedastic Noise Models
Sascha Xu, Alexander Marx, Osman A Mian, Jilles Vreeken
Spotlight Presentations 2
2:15pm - 2:30pm:
On Causal Inference for Data-free Structured Pruning
Martin Ferianc, Anush Sankaran, Olivier Mastropietro, Ehsan Saboori, Quentin Cappart
2:30pm - 2:45pm:
Gated Information Bottleneck for Generalization in Sequential Environments
Francesco Alesiani, Shujian Yu, Xi Yu
2:45pm - 3:00pm:
Probability trees and the value of a single intervention
Workshop Schedule (in EST)
8:00am - 8:15am: Opening Remarks
8:15am - 8:45am: Invited Talk by Nihat Ay
8:45am - 9:15am: Invited Talk by Mihaela van der Schaar
9:15am - 9:30am: Q & A
9:30am - 10:15am: Spotlight Presentations 1
10:15am - 11:00am: Social on Virtual Chair
11:00am - 12:00pm: Mentorship Session
12:00pm - 1:00pm: Lunch Break
1:00pm - 1:30pm: Invited Talk by Volker Roth
1:30pm - 2:00pm: Invited Talk by Christopher Quinn
2:00pm - 2:15pm: Q & A
2:15pm - 3:00pm: Spotlight Presentations 2
3:00pm - 3:45pm: Social on Virtual Chair
3:45pm - 4:00pm: Closing Remarks
Murat Kocaoglu, Chair (Purdue University)
Negar Kiyavash (EPFL)
Todd Coleman (Stanford University)
Alexander Marx, Amin Jaber, Biwei Huang, Jalal Etesami, Juan Correa, Kailash Budhathoki, Karthikeyan Shanmugam, Kristjan Greenewald, Maria Skoularidou, Md Musfiqur Rahman, Mohammad Ali Javidian, Sanjay Shakkottai, Sebastien Lachapelle, Shohei Shimizu, Sonali Parbhoo, Spencer Compton, Vasant Honavar