Skip to yearly menu bar Skip to main content

Invited Talk
Workshop: Interpretable Machine Learning for Complex Systems

Why Interpretability: A Taxonomy of Interpretability and Implications for Principled Evaluation (Finale Doshi-Velez)


With a growing interest in interpretability, there is an increasing need to characterize what exactly we mean by it and how to sensibly compare the interpretability of different approaches. In this talk, I suggest that our current desire for "interpretability" is as vague as asking for "good predictions" -- a desire that. while entirely reasonable, must be formalized into concrete needs such as high average test performance (perhaps held-out likelihood is a good metric) or some kind of robust performance (perhaps sensitivity or specificity are more appropriate metrics). This objective of this talk is to start a conversation to do the same for interpretability: I will describe distinct, concrete objectives that all fall under the umbrella term of interpretability and how each objective suggests natural evaluation procedures. I will also describe highlight important open questions in the evaluation of interpretable models.

Joint work with Been Kim, and the product of discussions with countless collaborators and colleagues.

Live content is unavailable. Log in and register to view live content