Deep Generative Learning for Jet Quenching

Abstract:
Progress in the theoretical understanding of parton branching dynamics that occurs within an expanding QGP relies on detailed and fair comparisons with experimental data for reconstructed jets. Such validation is only meaningful when the computed object, be it analitically or via event generation, accounts for the complexity of experimentally reconstructed jets. The reconstruction of jets in heavy ion collisions involves a, necessarily imperfect, subtraction of the large and fluctuating background: reconstructed jets always include background contamination.

The identification of jet quenching effects, that is modifications of the branching dynamics by interaction with QGP leading to changes on jet observables, should be done against a baseline that accounts for possible background contamination on unmodified jets. In practical terms, jet quenching effects are only those not present in samples of vacuum jets that have been embedded in a realistic heavy-ion background and where subtraction has been carried out analogously to that in the heavy ion case and as close as possible to what is done experientally.

Using the extensively validated JEWEL event generator, we performed an extensive survey of the sensitivity to background effects of commonly used jet observables. Further, we have assessed the robustness of Machine Learning studies aimed at classifying jets according to their degree of modification by the QGP to a reference where background contamination is accounted for.

Aiming at obtaining a jet by jet tagger for the quenching effect in a realistic experimental setting, the previous study has gave us the opportunity to study the usage of sophisticated architectures for the discrimination of pp and PbPb jets, as a proxy to discriminate quenched and unquenched jets in PbPb, such as transformers and energy flow networks, accounting for background contamination effects. These studies are furhter complemented by Anomaly Detection (AD) studies using Deep Generative Learning models, namely VAEs and beta-VAEs attempting to identify the quenching effect as an anomaly, again with bacground contamination effects accounted for.