Learning Interpretable Models with Causal Guarantees

By Carolyn Kim, Osbert Bastani. 2019

19 citations recorded by the source corpus.

Machine learning has shown much promise in helping improve the quality of medical, legal, and economic 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 causal interpretable models---from observational data---that can be used to predict individual treatment effects. Our framework can be used with any algorithm for learning interpretable models. 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.

Subfields: Artificial Intelligence, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations (2019, neutral): “predictive models that are human understandable [3, 8, 11, 14].”
Evaluating Explanation Without Ground Truth in Interpretable Machine Learning (2019, background): “The first limitation lies in the lack of causal perspective [17] in explanation evaluation.”
Generative causal explanations of black-box classifiers (2020, methodology): “Generative models have been used to compute interventions that respect the data distribution [51, 36, 19, 52], a key idea in this paper.”