A generic anti-QCD jet tagger

Abstract

New particles beyond the Standard Model might be produced with a very high boost, for instance if they result from the decay of a heavier particle. If the former decay hadronically, then their signature is a single massive fat jet which is difficult to separate from QCD backgrounds. Jet substructure and machine learning techniques allow for the discrimination of many specific boosted objects from QCD, but the scope of possibilities is very large, and a suite of dedicated taggers may not be able to cover every possibility - in addition to making experimental searches cumbersome. In this paper we describe a generic model-independent tagger that is able to discriminate a wide variety of hadronic boosted objects from QCD jets using N-subjettiness variables, with a significance improvement varying between 2 and 8. This is in addition to any improvement that might come from a cut on jet mass. Such a tagger can be used in model-independent searches for new physics yielding fat jets. We also show how such a tagger can be applied to signatures over a wide range of jet masses without sculpting the background distributions, allowing to search for new physics as bumps on jet mass distributions.Comment: Main text: 19 page

Running bumps from stealth bosons

“…The cross section times efficiency of the injected signals is given in Table 1. We note in passing that, as previously seen for the τ 21 and D 2 variables [3,25], the efficiency for stealth bosons of a cut on two-subjettiness, as measured by N 1 2 , is smaller than for the QCD background. The jet mass distributions at the different stages of the N 1 2 selection are presented for the three scenarios in the top, left panels of Figs.…”

“…In particular, a generic anti-QCD tagger [25] that does not penalise multi-pronged signals always constitutes an advantage when looking for signals yielding non-standard jets.…”

What is the machine learning?

“…This could reveal new variables for traditional searches. Finally, what information is contained in jets could be explored with planing to complement the existing saturation analyses [11,12]. We intend to investigate many of these applications in future studies.…”

“…In what follows, as we study planing we will also utilize a technique (see [2][3][4][5]11,12]) which we refer to as "saturation," that compares a network trained on only low-level inputs with networks trained after adding higher-level variables. Saturation provides a tool to ensure that our networks are sufficiently deep, by checking that the new network's performance does not improve by much.…”

“…We use the "uniform phase space" scheme to flatten discriminating variables, which was introduced in [6] to quantify the information learned by deep neural networks. For other suggestions on testing what the machines are learning, see [7][8][9][10][11][12]. A nice summary of these ideas can be found in [13].…”