Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis

MCML Authors

Christian Alexander Scholbeck

Dr.

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Julia Moosbauer

Dr.

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Giuseppe Casalicchio

Dr.

→ Group Bernd Bischl
 Statistical Learning and Data Science

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

Abstract

We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental modeling, engineering, or economics. We address both researchers and practitioners, calling attention to the benefits of a unified SA-based view of explanations in ML and the necessity to fully credit related work. We bridge the gap between both fields by formally describing how (a) the ML process is a system suitable for SA, (b) how existing ML interpretation methods relate to this perspective, and (c) how other SA techniques could be applied to ML.

misc SMC+23

---

Preprint

Dec. 2023

---

Authors

C. A. Scholbeck • J. Moosbauer • G. Casalicchio • H. Gupta • B. Bischl • C. Heumann

---

Links

arXiv

---

Research Area

 A1 | Statistical Foundations & Explainability