Ecole d'ingénieur et centre de recherche en Sciences du numérique

Seminar: DATA TALK

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

Data Science

Date: 21 janvier 2020

Lieu: 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. Bio: Damien Garreau is assistant professor at the University Cote d'Azur in the Probability and Statistics team. He is also part of the Inria Sophia-Antipolis Maasai team. From 2017 to 2019, he was a postdoctoral researcher in the Max Planck Institute for Intelligent Systems (Tuebingen, Germany), where he worked with Ulrike von Luxburg. He did his PhD at Inria Paris in the Sierra team from 2014 to 2017, under the supervision of Sylvain Arlot and Gerard Biau.