Can I read Optimal Explanations of Linear Models on EtoBox?

Optimal Explanations of Linear Models by Bertsimas, Dimitris; Delarue, Arthur; Jaillet, Patrick; Martin, Sebastien is a scholarly article available to read on EtoBox.

What is Optimal Explanations of Linear Models about?

When predictive models are used to support complex and important decisions, the ability to explain a model's reasoning can increase trust, expose hidden biases, and reduce vulnerability to adversarial attacks. However, attempts at interpreting models are often ad hoc and application-specific, and the concept of interpretability itself is not well-defined. We propose a general optimization framework to create explanations for linear models. Our methodology decomposes a linear model into a sequence of models of increasing complexity using coordinate updates on the coefficients. Computing this decomposition optimally is a difficult optimization problem for which we propose exact algorithms and scalable heuristics. By solving this problem, we can derive a parametrized family of interpretability metrics for linear models that generalizes typical proxies, and study the tradeoff between interpretability and predictive accuracy.

Author

Bertsimas, Dimitris; Delarue, Arthur; Jaillet, Patrick; Martin, Sebastien

Published

2019

Language

EN