Resources

This page collects references and further reading to help understand the library, the theory behind JPTs, and related work.

Papers

  • Joint Probability Trees — the original pyjpt paper: Nyga, Picklum, Schierenbeck, Beetz (2023). arXiv:2302.07167

  • Probabilistic Circuits: A Unifying Framework — [CVVdB20]. Introduces the probabilistic circuit framework that JPTs build upon.

  • CART: Classification and Regression Trees — Breiman et al. (1984). The basis for the tree-construction algorithm used in JPTs.

External Tools

  • scikit-learn — used for dataset utilities and model evaluation in the tutorial notebooks.

  • pandas — DataFrame-based data handling used throughout the API.

  • MLflow — optional experiment tracking integration; see MLFlow Integration.

[Cha21]

Sourav Chatterjee. A new coefficient of correlation. Journal of the American Statistical Association, 116(536):2009–2022, 2021. doi:10.1080/01621459.2020.1758115.

[CVVdB20]

YooJung Choi, Antonio Vergari, and Guy Van den Broeck. Probabilistic circuits: a unifying framework for tractable probabilistic models. oct 2020. URL: http://starai.cs.ucla.edu/papers/ProbCirc20.pdf.

[DAG24]

Christoph Dalitz, Lena Arning, and Steffen Goebbels. A simple bias reduction for Chatterjee's correlation. Journal of Statistical Theory and Practice, 18(2):1–15, 2024. doi:10.1007/s42519-024-00399-y.