Causality is a fundamental notion in science and engineering. In the past few decades, some of the most influential developments in the study of causal discovery, causal inference, and the causal treatment of machine learning have resulted from cross-disciplinary efforts. In particular, a number of machine learning and statistical analysis techniques have been developed to tackle classical causal discovery and inference problems. On the other hand, the causal view has been shown to be able to facilitate formulating, understanding, and tackling a number of hard machine learning problems in transfer learning, reinforcement learning, and deep learning.

We invite submissions to the 3rd conference on Causal Learning and Reasoning (CLeaR), and welcome paper submissions that describe new theory, methodology, and/or applications relevant to any aspect of causal learning and reasoning in the fields of artificial intelligence and statistics. Submitted papers will be evaluated based on their novelty, technical quality, and potential impact. Experimental methods and results are expected to be reproducible, and authors are strongly encouraged to make code and data available. We also encourage submissions of proof-of-concept research that puts forward novel ideas and demonstrates potential for addressing problems at the intersection of causality and machine learning.CLeaR 2024 will be held at the Pallisades Room, 3rd Floor, Carnesale Commons, UC Los Angeles, California from April 1 to 3, 2024.
Topics of submission may include, but are not limited to:

Machine learning building on causal principles
Causal discovery in complex environments
Efficient causal discovery in large-scale datasets
Causal effect identification and estimation
Causal generative models for machine learning
Unsupervised and semi-supervised deep learning connected to causality
Machine learning with heterogeneous data sources
Benchmark for causal discovery and causal reasoning
Reinforcement learning
Fairness, accountability, transparency, explainability, trustworthiness, and recourse
Applications of any of the above to real-world problems
Causal representation learning
Causal inference in philosophy and psychology

Different from last year, there will be a single track for all submissions (no separate call for dataset submissions). The program at the conference will highlight new applications of causality to real-world problems, benchmark datasets, or benchmark methodologies.