Abstract
We investigate deep learning autoencoders for the unsupervised recognition of phase transitions in physical systems formulated on a lattice. We focus our investigation on the 2-dimensional ferromagnetic Ising model and then test the application of the autoencoder on the anti-ferromagnetic Ising model. We use spin configurations produced for the 2-dimensional ferromagnetic and anti-ferromagnetic Ising model in zero external magnetic field. For the ferromagnetic Ising model, we study numerically the relation between one latent variable extracted from the autoencoder to the critical temperature Tc. The proposed autoencoder reveals the two phases, one for which the spins are ordered and the other for which spins are disordered, reflecting the restoration of the ℤ2 symmetry as the temperature increases. We provide a finite volume analysis for a sequence of increasing lattice sizes. For the largest volume studied, the transition between the two phases occurs very close to the theoretically extracted critical temperature. We define as a quasi-order parameter the absolute average latent variable z̃, which enables us to predict the critical temperature. One can define a latent susceptibility and use it to quantify the value of the critical temperature Tc(L) at different lattice sizes and that these values suffer from only small finite scaling effects. We demonstrate that Tc(L) extrapolates to the known theoretical value as L →∞ suggesting that the autoencoder can also be used to extract the critical temperature of the phase transition to an adequate precision. Subsequently, we test the application of the autoencoder on the anti-ferromagnetic Ising model, demonstrating that the proposed network can detect the phase transition successfully in a similar way.
Graphical abstract
![](http://media.springernature.com/lw685/springer-static/image/art%3A10.1140%2Fepjb%2Fe2020-100506-5/MediaObjects/10051_2020_3204_Fig1_HTML.jpg)
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
P. Broecker, F.F. Assaad, S. Trebst, arXiv:1707.00663 (2017)
P. Broecker, J. Carrasquilla, R.G. Melko, S. Trebst, Sci. Rep. 7, 8823 (2017)
J. Carrasquilla, R.G. Melko, Nat. Phys. 13, 431 (2017)
K. Ch’ng, J. Carrasquilla, R.G. Melko, E. Khatami, Phys. Rev. X 7, 031038 (2017)
C Giannetti, B Lucini, D Vadacchino, Nucl. Phys. B 944, 114639
W. Hu, R.R.P. Singh, R.T. Scalettar, Phys. Rev. E 95, 062122 (2017)
R.B. Jadrich, B.A. Lindquist, T.M. Truskett, J. Chem. Phys. 149, 194109 (2018)
K. Kashiwa, Y. Kikuchi, A. Tomiya, Prog. Theor. Phys. 2019, 083A04 (2019)
D. Kim, D.-H. Kim, Phys. Rev. E 98, 022138 (2018)
E. van Nieuwenburg, Y.-H. Liu, S. Huber, Nat. Phys. 13, 435 (2017)
J. Venderley, V. Khemani, E.-A. Kim, Phys. Rev. Lett. 120, 257204 (2018)
L. Wang, Phys. Rev. B 94, 195105 (2016)
S.J. Wetzel, Phys. Rev. E 96, 022140 (2017)
N. Yoshioka, Y. Akagi, H. Katsura, Phys. Rev. B 97, 205110 (2018)
W. Zhang, J. Liu, T.-C. Wei, arXiv:1804.02709 (2018)
X.L. Zhao, L.B. Fu, arXiv:1808.01731 (2018)
K. Zhou, G. Endrödi, L.-G. Pang, H. Stöcker, arXiv:1810.12879
S. Foreman, J. Giedt, Y. Meurice, J. Unmuth-Yockey, Phys. Rev. E 98, 052129 (2018)
S.J. Wetzel, Phys. Rev. E 96, 022140 (2017)
A. Morningstar, R.G. Melko, arXiv:1708.04622
G. Cossu, L. Del Debbio, T. Giani, A. Khamseh, M. Wilson, arXiv:1810.11503
S.S. Funai, D. Giataganas, arXiv:1810.08179
S.J. Wetzel, M. Scherzer, Phys. Rev. B 96, 184410 (2017)
I. Luchnikov, A. Ryzhov, P.-J.C. Stas, S.N. Filippov, H. Ouerdane, arXiv:1910.03957
M. Cristoforetti, G. Jurman, A.I. Nardelli, C. Furlanello, arXiv:1705.09524 [hep-lat]
R. Zhang, B. Wei, D. Zhang, J.-J. Zhu, K. Chang, Phys. Rev. B 99, 094427 (2019)
Z. Li, M. Luo, X. Wan, Phys. Rev. B 99, 075418 (2019)
R.H. Swendsen, J.-S. Wang, Phys. Rev. Lett. 58, 88 (1987)
J.-S. Wang, R.H. Swendsen, Physica A 167, 579 (1990)
C.M. Fortuin, P.W. Kasteleyn, Physica 57, 564 (1972)
P.W. Kasteleyn, C.M. Fortuin, Phase Transitions in Lattice Systems with Random Local Properties, in Proceedings of the International Conference on Statistical Mechanics held 9–14 September, 1968 in Kyoto, (Phys. Soc. Jpn. J. Suppl. 26, 11 (1969))
H. Gould, J. Tobochnik, W. Christian, in An introduction to computer simulation methods (Addison-Wesley, 1996) Vol. 1
J. Cardy, Scaling and Renormalization in Statistical Physics (Cambridge University Press, 1996)
G. Jaeger, Arch. Hist. Exact Sci. 53, 81 (1998)
H. Bourlard, Y. Kamp, Biol. Cybern. 59, 291 (1988)
G.E. Hinton, R.S. Zemel, in NIPS’93: Proceedings of the 6th International Conference on Neural Information Processing Systems, November 1993 (Morgan Kaufmann Publishers Inc., USA, 1993), pp. 3–10
N. Le Roux, Y. Bengio, Neural Comput. 20, 1631 (2008)
D.P. Kingma, M. Welling, arXiv:1312.6114
P. Vincent, H. Larochelle, Y. Bengio, P.-A. Manzagol, Extracting and composing robust features with denoising autoencoders, in Proceedings of the 25th International Conference on Machine Learning (ACM, 2008), pp. 1096–1103
P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, P.-A. Manzagol, J. Mach. Learn. Res. 11, 3371 (2010)
G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R.R. Salakhutdinov, arXiv:1207.0580
F. Chollet, et al., Keras, https://keras.io (2015)
M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, et al., in OSDI’16: Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, November 2016 (USENIX Association, USA, 2016), pp. 265–283
J. Hubbard Proc. Roy. Soc. London Ser. A 276, 238 (1963)
J.M. Kosterlitz, D.J. Thouless, J. Phys. C 6, 1181 (1973)
P.B. Arnold, G.D. Moore, Phys. Rev. E 64, 066113 (2001) [Erratum: Phys. Rev. E 68, 049902 (2003)]
K. Binder, Phys. Rev. Lett. 47, 693 (1981)
K. Vollmayr, J.D. Reger, M. Scheucher, K. Binder, Z. Phys. B 91, 113 (1993)
R. Balian, R. Maynard, G. Toulouse, Ill-Condensed Matter (Co-Published with North-Holland Publishing Co., 1984)
A. Athenodorou, M. Teper, JHEP 01, 063 (2019)
J. Liddle, M. Teper, arXiv:0803.2128
C. Alexandrou, A. Apseros, A. Athenodorou, C. Chrysostomou, C. Havadjia, S. Paul, S. Siakas, in preparation
Acknowledgments
Open Access funding provided by Università di Pisa within the CRUICARE Agreement.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
The EPJ Publishers remain neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
About this article
Cite this article
Alexandrou, C., Athenodorou, A., Chrysostomou, C. et al. The critical temperature of the 2D-Ising model through deep learning autoencoders. Eur. Phys. J. B 93, 226 (2020). https://doi.org/10.1140/epjb/e2020-100506-5
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1140/epjb/e2020-100506-5