Timezone: »

 
Poster
Learning outside the Black-Box: The pursuit of interpretable models
Jonathan Crabbe · Yao Zhang · William Zame · Mihaela van der Schaar

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1491
in Poster Session 6 »

Machine learning has proved its ability to produce accurate models -- but the deployment of these models outside the machine learning community has been hindered by the difficulties of interpreting these models. This paper proposes an algorithm that produces a continuous global interpretation of any given continuous black-box function. Our algorithm employs a variation of projection pursuit in which the ridge functions are chosen to be Meijer G-functions, rather than the usual polynomial splines. Because Meijer G-functions are differentiable in their parameters, we can "tune" the parameters of the representation by gradient descent; as a consequence, our algorithm is efficient. Using five familiar data sets from the UCI repository and two familiar machine learning algorithms, we demonstrate that our algorithm produces global interpretations that are both faithful (highly accurate) and parsimonious (involve a small number of terms). Our interpretations permit easy understanding of the relative importance of features and feature interactions. Our interpretation algorithm represents a leap forward from the previous state of the art.

Author Information

Jonathan Crabbe (University of Cambridge)
Yao Zhang (University of Cambridge)
William Zame (UCLA)

William Zame is Distinguished Professor of Economics and Mathematics. His interests include Economic Theory, Experimental Economics, Engineering and Mathematics, and Machine Learning and Medicine. He is a Fellow of the Econometric Society and the Society for the Advancement of Economic Theory and a former Fellow of the John Simon Guggenheim Foundation .

Mihaela van der Schaar (University of Cambridge)

More from the Same Authors