The NFLikelihood: an unsupervised DNNLikelihood from Normalizing Flows

TL;DR

The paper introduces NFLikelihood, an unsupervised deep neural network approach using normalizing flows to model complex high-dimensional likelihoods in high energy physics analyses, offering a flexible alternative to supervised methods.

Contribution

It presents NFLikelihood, a novel unsupervised method based on normalizing flows for modeling likelihoods in high energy physics, demonstrated on realistic LHC and EFT analysis examples.

Findings

Successfully models complex likelihoods in HEP analyses

Demonstrates advantages of unsupervised over supervised approaches

Shows potential for integration with existing analysis frameworks

Abstract

We propose the NFLikelihood, an unsupervised version, based on Normalizing Flows, of the DNNLikelihood proposed in Ref.[1]. We show, through realistic examples, how Autoregressive Flows, based on affine and rational quadratic spline bijectors, are able to learn complicated high-dimensional Likelihoods arising in High Energy Physics (HEP) analyses. We focus on a toy LHC analysis example already considered in the literature and on two Effective Field Theory fits of flavor and electroweak observables, whose samples have been obtained throught the HEPFit code. We discuss advantages and disadvantages of the unsupervised approach with respect to the supervised one and discuss possible interplays of the two.