# Learning Interpretable Models with Causal Guarantees

arXiv: https://arxiv.org/abs/1901.08576 · HTML: https://mlsanity.com/paper/1901.08576/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2019.

## Built on by (most cited first, 11 of 11)

- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability](https://mlsanity.com/paper/2206.08363/) (2022)
- [Explainable AI for Bioinformatics: Methods, Tools, and Applications](https://mlsanity.com/paper/2212.13261/) (2022)
- [Generative Adversarial Model-Based Optimization via Source Critic Regularization](https://mlsanity.com/paper/2402.06532/) (2024)
- [Unsupervised Causal Binary Concepts Discovery with VAE for Black-box Model Explanation](https://mlsanity.com/paper/2109.04518/) (2021)
- [Causal Inference for Banking Finance and Insurance A Survey](https://mlsanity.com/paper/2307.16427/) (2023)
- [DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation](https://mlsanity.com/paper/2406.00611/) (2024)
- [CausalKANs: interpretable treatment effect estimation with Kolmogorov-Arnold networks](https://mlsanity.com/paper/2509.22467/) (2025)
- [Navigating causal deep learning](https://mlsanity.com/paper/2212.00911/) (2022)
- [Information-theoretic Evolution of Model Agnostic Global Explanations](https://mlsanity.com/paper/2105.06956/) (2021)
- [Kolmogorov-Arnold causal generative models](https://mlsanity.com/paper/2603.20184/) (2026)

## Abstract (arXiv)

Machine learning has shown much promise in helping improve the quality of medical, legal, and financial decision-making. In these applications, machine learning models must satisfy two important criteria: (i) they must be causal, since the goal is typically to predict individual treatment effects, and (ii) they must be interpretable, so that human decision makers can validate and trust the model predictions. There has recently been much progress along each direction independently, yet the state-of-the-art approaches are fundamentally incompatible. We propose a framework for learning interpretable models from observational data that can be used to predict individual treatment effects (ITEs). In particular, our framework converts any supervised learning algorithm into an algorithm for estimating ITEs. Furthermore, we prove an error bound on the treatment effects predicted by our model. Finally, in an experiment on real-world data, we show that the models trained using our framework significantly outperform a number of baselines.