Julian Dörfler — accepted AI-conference papers

2025

From Probability to Counterfactuals: the Increasing Complexity of Satisfiability in Pearl's Causal Hierarchy

Julian Dörfler, Benito van der Zander, Markus Bläser, Maciej Liskiewicz

ICLR 2025poster

The framework of Pearl's Causal Hierarchy (PCH) formalizes three types of reasoning: probabilistic (i.e. purely observational), interventional, and counterfactual, that reflect the progressive sophistication of human thought regarding causation. We investigate the computational complexity aspects of…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

On the Complexity of Identification in Linear Structural Causal Models

Julian Dörfler, Benito van der Zander, Markus Bläser, Maciej Liskiewicz

NeurIPS 2024poster

Learning the unknown causal parameters of a linear structural causal model is a fundamental task in causal analysis. The task, known as the problem of identification, asks to estimate the parameters of the model from a combination of assumptions on the graphical structure of the model and observa…

Cited by 0 Source ↗PDF ↗Scholar ↗