Graduate School and Research Center in Digital Sciences

Seminar: DATA TALK

Damien Garreau - Assistant Professor at the University Cote d'Azur

Data Science

Date: January 21, 2020

Location: Eurecom - EURECOM

Title: Explaining the Explainer: A First Theoretical Analysis of LIME Abstract: Machine learning is used more and more often for sensitive applications, sometimes replacing humans in critical decision-making processes. As such, interpretability of these algorithms is a pressing need. One popular algorithm to provide interpretability is LIME (Local Interpretable Model-Agnostic Explanation). In this talk, I will present a first theoretical analysis of LIME. In particular, we derived closed-form expressions for the coefficients of the interpretable model when the function to explain is linear. The good news is that these coefficients are proportional to the gradient of the function to explain: LIME indeed discovers meaningful features. However, our analysis also reveals that poor choices of parameters can lead LIME to miss important features.