Abstract
Machine learning (ML) techniques have seen increasing use in recent years in complementing traditional HPC solutions to physical systems problems. While the scientific community has been rapidly adopting such techniques, it is still unclear how different ML techniques compare in terms of accuracy. In this paper we address this question by designing and training a neural network and comparing its performance to traditional classification models using as a case study a non-interacting quantum system on a graph structure. We build a classifier with the ability to distinguish extended from localized quantum states based on their different structure and compare it with other commonly used ML classifiers. Our results show high accuracy for certain ML models in most cases, whereas others are less effective.
Supported by the Greek Research Technology Development and Innovation Action “RESEARCH - CREATE - INNOVATE”, Operational Programme on Competitiveness, Entrepreneurship and Innovation 2014–2020, Grant T1E\(\Delta \)K-04819.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539
Biamonte, J., Wittek, P., Pancotti, N. et al.: Quantum machine learning. Nature 549, 195–202 (2017). https://doi.org/10.1038/nature23474
Carrasquilla, J., Melko, R. G.: Machine learning phases of matter. Nat. Phys. 13, 431–434 (2017). https://doi.org/10.1038/nphys4035
Carrasquilla, J.: Machine Learning for Quantum Matter. arXiv:2003.11040 (2020) https://arxiv.org/abs/2003.11040
Carleo, G., et al.: Machine learning and the physical sciences. Rev. Mod. Phys. 91, 045002 (2019). https://doi.org/10.1103/RevModPhys.91.045002
Schmidt, J., Marques, M.R.G., Botti, S. et al.: Recent advances and applications of machine learning in solid-state materials science. NNI Comput Mater 5, 83 (2019). https://doi.org/10.1038/s41524-019-0221-0
Yu, S., Piao, X., Park, N.: Machine learning identifies scale-free properties in disordered materials. Nat. Commun. 11, 4842 (2020). https://doi.org/10.1038/s41467-020-18653-9
Ohtsuki T., Mano T.: Drawing of phase diagrams random quantum systems by deep learning the wave functions. J. Phys. Soc. Jpn. 89, 022001 (2020). https://doi.org/10.7566/JPSJ.89.022001
Preskill, J.: Quantum Computing in the NISQ era and beyond. Quantum 2, 79 (2018). https://doi.org/10.22331/q-2018-08-06-79
Anderson, P.W.: Absence of diffusion in certain random lattices. Phys. Rev. 109, 1492 (1958). https://doi.org/10.1103/PhysRev.109.1492
Altman, E.: Many-body localization and quantum thermalization. Nat. Phys. 14, 979–983 (2018). https://doi.org/10.1038/s41567-018-0305-7
Altshuler, B. L., Cuevas, L., Ioffe, L. B., Kravtsov, V. E.: Nonergodic phases in strongly disordered random regular graphs. Phys. Rev. Lett. 117, 156601 (2016). https://doi.org/10.1103/PhysRevLett.117.156601
Atas, Y.Y., Bogomolny, E., Giraud, O., Roux, G.: Distribution of the ratio of consecutive level spacings in random matrix ensembles. Phys. Rev. Lett. 110 084101 (2013). https://doi.org/10.1103/PhysRevLett.110.084101
Tikhonov, K.S., Mirlin, A.D., Skvortsov, M.A.: Anderson localization and ergodicity on random regular graphs. Phys. Rev. B 94, 220203(R) (2016). https://doi.org/10.1103/PhysRevB.94.220203
Zhang, W., Wang, L., Wang, Z.: Interpretable machine learning study of the many-body localization transition in disordered quantum using spin chains. Phys. Rev. B 99, 054208 (2019). https://doi.org/10.1103/PhysRevB.99.054208
Alexandru, A., Bedaque, B. F., Lawrence, S.: Quantum algorithms for disordered physics. Phys. Rev. A 101, 032325 (2020). https://doi.org/10.1103/PhysRevA.101.032325
Barzen, J., Leymann, F.: Quantum humanities: a vision for quantum computing in digital humanities. SICS Softw.-Inten. Cyber-Phys. Syst. 153–158 (2019). https://doi.org/10.1007/s00450-019-00419-4
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Stamatiou, G.T., Magoutis, K. (2021). Investigating the Use of Machine Learning Techniques in a Random Physical System. In: Barzen, J. (eds) Service-Oriented Computing. SummerSOC 2021. Communications in Computer and Information Science, vol 1429. Springer, Cham. https://doi.org/10.1007/978-3-030-87568-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-87568-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87567-1
Online ISBN: 978-3-030-87568-8
eBook Packages: Computer ScienceComputer Science (R0)