Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis
This is an incremental position paper aimed at researchers and practitioners to unify explanations in ML with sensitivity analysis.
The paper argues that machine learning model interpretations can be viewed as sensitivity analysis, bridging the gap by formally describing how ML processes relate to SA and how SA techniques could be applied to ML.
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.