Position: Probabilistic Modelling is Sufficient for Causal Inference
Authors: Bruno Kacper Mlodozeniec, David Krueger, Richard E Turner
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we want to make it clear that you can answer any causal inference question within the realm of probabilistic modelling and inference, without causal-specific tools or notation. Through concrete examples, we demonstrate how causal questions can be tackled by writing down the probability of everything. Lastly, we reinterpret causal tools as emerging from standard probabilistic modelling and inference, elucidating their necessity and utility. ... Heeding Pearl (2019b) s call for concrete examples, we will demonstrate the probabilistic approach on simple examples of causal inference problems in turn, interventional (Section 2) and counterfactual (Section 3). For each, we will illustrate how one can solve it by writing down the probability of everything. |
| Researcher Affiliation | Academia | 1University of Cambridge 2Max Planck Institute for Intelligent Systems, Tübingen 3MILA 4The Alan Turing Institute. Correspondence to: Bruno Mlodozeniec <EMAIL>. |
| Pseudocode | No | The paper describes methods and rules (e.g., in 'A.3. The rules of the do-calculus') but does not present any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code or links to code repositories. |
| Open Datasets | No | The paper uses a 'log-normal aspirin model' for its examples and refers to a synthetic dataset 'D = {(zi, ti, yi)}N i=1'. This dataset is generated by the model for illustrative purposes and is not a publicly available dataset with concrete access information. |
| Dataset Splits | No | The paper uses a theoretical log-normal aspirin model and synthetic data for illustrative examples. It does not describe any real datasets or their splits (e.g., training, validation, test splits) for empirical evaluation. |
| Hardware Specification | No | The paper is theoretical and focuses on conceptual demonstrations. It does not describe any experimental hardware used. |
| Software Dependencies | No | The paper is theoretical and does not describe the specific software libraries or tools with version numbers that would be needed to replicate any experimental results. |
| Experiment Setup | No | The paper is theoretical and uses illustrative examples based on a model. It does not detail specific experimental setups, hyperparameters, or training configurations for empirical evaluation. |