What is the Machine Learning?

TL;DR

This paper introduces a data planing technique to improve interpretability of machine learning models in physics by identifying key variables and understanding the nature of decision boundaries, enhancing transparency and diagnostic capability.

Contribution

The paper presents a novel data planing method that helps interpret machine learning models in physics by analyzing variable importance and boundary linearity, addressing transparency concerns.

Findings

Effective in identifying discriminating variables

Diagnoses linear vs. non-linear decision boundaries

Applicable to complex physics scenarios like LHC resonance searches

Abstract

Applications of machine learning tools to problems of physical interest are often criticized for producing sensitivity at the expense of transparency. To address this concern, we explore a data planing procedure for identifying combinations of variables -- aided by physical intuition -- that can discriminate signal from background. Weights are introduced to smooth away the features in a given variable(s). New networks are then trained on this modified data. Observed decreases in sensitivity diagnose the variable's discriminating power. Planing also allows the investigation of the linear versus non-linear nature of the boundaries between signal and background. We demonstrate the efficacy of this approach using a toy example, followed by an application to an idealized heavy resonance scenario at the Large Hadron Collider. By unpacking the information being utilized by these algorithms, this method puts in context what it means for a machine to learn.