Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States

Araz, Jack Y.; Spannowsky, Michael

doi:10.1007/jhep08(2021)112

Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States

Araz, Jack Y.; Spannowsky, Michael

Authors

Dr Jack Araz jack.araz@durham.ac.uk
Academic Visitor

Michael Spannowsky

Abstract

Tensor Networks are non-trivial representations of high-dimensional tensors, originally designed to describe quantum many-body systems. We show that Tensor Networks are ideal vehicles to connect quantum mechanical concepts to machine learning techniques, thereby facilitating an improved interpretability of neural networks. This study presents the discrimination of top quark signal over QCD background processes using a Matrix Product State classifier. We show that entanglement entropy can be used to interpret what a network learns, which can be used to reduce the complexity of the network and feature space without loss of generality or performance. For the optimisation of the network, we compare the Density Matrix Renormalization Group (DMRG) algorithm to stochastic gradient descent (SGD) and propose a joined training algorithm to harness the explainability of DMRG with the efficiency of SGD.

Citation

Araz, J. Y., & Spannowsky, M. (2021). Quantum-inspired event reconstruction with Tensor Networks: Matrix Product States. Journal of High Energy Physics, 2021(8), https://doi.org/10.1007/jhep08%282021%29112

Journal Article Type	Article
Acceptance Date	Aug 1, 2021
Online Publication Date	Aug 23, 2021
Publication Date	2021
Deposit Date	Nov 9, 2021
Publicly Available Date	Nov 9, 2021
Journal	Journal of High Energy Physics
Print ISSN	1126-6708
Electronic ISSN	1029-8479
Publisher	Scuola Internazionale Superiore di Studi Avanzati (SISSA)
Peer Reviewed	Peer Reviewed
Volume	2021
Issue	8
DOI	https://doi.org/10.1007/jhep08%282021%29112

Files

Published Journal Article (3.8 Mb)
PDF

Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/

Copyright Statement
This article is distributed under the terms of the Creative Commons Attribution License (CC-BY 4.0), which permits any use, distribution and reproduction in any medium, provided the original author(s) and source are credited.