Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
TL
TL;DR
This work trains one such network to identify and assign the decay products of each top quark unambiguously and without combinatorial explosion, and significantly outperforms existing state-of-the-art methods.
Abstract
Top quarks are the most massive particle in the Standard Model and are produced in large numbers at the Large Hadron Collider. As the only quark to decay prior to hadronization, they have a complex detector signature and require special reconstruction techniques. The most common decay mode, the so-called "all-hadronic" channel, results in a 6-jet final state which is particularly difficult to reconstruct in $pp$ collisions due to the large number of permutations possible. We present a novel approach to this class of problem, based on neural networks using a generalized attention mechanism, that we call Symmetry Preserving Attention Networks (SPA-Net). We train one such network to identify and assign the decay products of each top quark unambiguously and without combinatorial explosion as an example of the power of this technique. This approach significantly outperforms existing state-of-the-art methods, correctly assigning all jets in 93.0\% of 6-jet events, 87.8\% of events with 7 jets, and 82.6\% of events with $\geq 8$ jets.
References51 items
1
Zero-permutation jet-parton assignment using a self-attention network
2
Graph neural networks in particle physics
3
Measurements of top-quark pair single- and double-differential cross-sections in the all-hadronic channel in $pp$ collisions at $\sqrt{s}=13~\mbox{TeV}$ using the ATLAS detector
4
Sherpa: Robust Hyperparameter Optimization for Machine Learning
5