Causal Theory

Causal theory aims to understand and model cause-and-effect relationships, focusing on inferring causal structures from observational data and predicting the effects of interventions. Current research emphasizes developing scalable algorithms, such as Bayesian methods and transformer models, to learn causal graphs, often relaxing constraints like acyclicity to handle complex systems and multi-scale temporal dynamics. This work is crucial for improving AI systems' ability to reason causally, leading to more reliable predictions and decision-making in various fields, including economics and natural sciences.

Papers