ML Interpretability: Simple Isn't Easy
It addresses the problem of defining interpretability for researchers and practitioners, but it is incremental as it builds on existing philosophical discussions.
The paper clarifies the nature of interpretability in ML by analyzing why simple models like linear models and decision trees are highly interpretable and how more general models retain some interpretability, finding that interpretability can be explicated clearly in specific cases.
The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the 'interpretability spectrum'. The reasons why some models, linear models and decision trees, are highly interpretable will be examined, and also how more general models, MARS and GAM, retain some degree of interpretability. I find that while there is heterogeneity in how we gain interpretability, what interpretability is in particular cases can be explicated in a clear manner.