HEP-PHLGNov 4, 2022

Decorrelation with conditional normalizing flows

arXiv:2211.02486v36 citationsh-index: 88
AI Analysis

This addresses the need for more effective discriminants in physics analyses by reducing unwanted correlations, though it appears incremental as it builds on existing normalizing flow methods.

The paper tackled the problem of constructing discriminants that are uncorrelated with protected attributes to enhance sensitivity in physics analyses, achieving almost no sculpting in the mass distribution of the background as a result.

The sensitivity of many physics analyses can be enhanced by constructing discriminants that preferentially select signal events. Such discriminants become much more useful if they are uncorrelated with a set of protected attributes. In this paper we show that a normalizing flow conditioned on the protected attributes can be used to find a decorrelated representation for any discriminant. As a normalizing flow is invertible the separation power of the resulting discriminant will be unchanged at any fixed value of the protected attributes. We demonstrate the efficacy of our approach by building supervised jet taggers that produce almost no sculpting in the mass distribution of the background.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes