Identifying topological order through unsupervised machine learning

Article metrics

Abstract

The Landau description of phase transitions relies on the identification of a local order parameter that indicates the onset of a symmetry-breaking phase. In contrast, topological phase transitions evade this paradigm and, as a result, are harder to identify. Recently, machine learning techniques have been shown to be capable of characterizing topological order in the presence of human supervision. Here, we propose an unsupervised approach based on diffusion maps that learns topological phase transitions from raw data without the need for manual feature engineering. Using bare spin configurations as input, the approach is shown to be capable of classifying samples of the two-dimensional XY model by winding number and capture the Berezinskii–Kosterlitz–Thouless transition. We also demonstrate the success of the approach on the Ising gauge theory, another paradigmatic model with topological order. In addition, a connection between the output of diffusion maps and the eigenstates of a quantum-well Hamiltonian is derived. Topological classification via diffusion maps can therefore enable fully unsupervised studies of exotic phases of matter.

Access optionsAccess options

Rent or Buy article

Get time limited or full article access on ReadCube.

from$8.99

All prices are NET prices.

Fig. 1: Topological classification using sample connectivity.
Fig. 2: Detection of topological order in the 1D XY model.
Fig. 3: Detection of topological order in the 2D XY model.
Fig. 4: Detection of topological order in the Ising gauge theory.
Fig. 5: Illustration of the diffusion map in the continuum limit.

Data availability

The data that support the plots within this paper and other findings of this study are available from the corresponding authors upon reasonable request.

Code availability

The code used to generate the results presented in this work can be found in the online version of the paper.

References

  1. 1.

    Nielsen, M. A. Neural Networks and Deep Learning (Determination Press, 2015).

  2. 2.

    Goodfellow, I., Bengio, Y. & Courville, A. Deep Learning (MIT Press, 2016).

  3. 3.

    Mehta, P. et al. A high-bias, low-variance introduction to machine learning for physicists. Preprint at https://arxiv.org/abs/1803.08823 (2018).

  4. 4.

    Mehta, P. & Schwab, D. J. An exact mapping between the variational renormalization group and deep learning. Preprint at https://arxiv.org/abs/1410.3831 (2014).

  5. 5.

    Carleo, G. & Troyer, M. Solving the quantum many-body problem with artificial neural networks. Science 355, 602–606 (2017).

  6. 6.

    Deng, D.-L., Li, X. & Das Sarma, S. Machine learning topological states. Phys. Rev. B 96, 195145 (2017).

  7. 7.

    Liu, J., Qi, Y., Meng, Z. Y. & Fu, L. Self-learning Monte Carlo method. Phys. Rev. B 95, 041101 (2017).

  8. 8.

    Torlai, G. et al. Neural-network quantum state tomography. Nat. Phy. (2018).

  9. 9.

    You, Y.-Z., Yang, Z. & Qi, X.-L. Machine learning spatial geometry from entanglement features. Phys. Rev. B 97, 045153 (2018).

  10. 10.

    Carleo, G., Nomura, Y. & Imada, M. Constructing exact representations of quantum many-body systems with deep neural networks. Nat. Commun. 9, 5322 (2018).

  11. 11.

    Spillard, S., Turner, C. J. & Meichanetzidis, K. Machine learning entanglement freedom. Int. J. Quantum Inf. 16, 1840002 (2018).

  12. 12.

    Carrasquilla, J. & Melko, R. G. Machine learning phases of matter. Nat. Phys. 13, 431–434 (2017).

  13. 13.

    Ch’ng, K., Carrasquilla, J., Melko, R. G. & Khatami, E. Machine learning phases of strongly correlated fermions. Phys. Rev. X 7, 031038 (2017).

  14. 14.

    Zhang, Y. & Kim, E.-A. Quantum loop topography for machine learning. Phys. Rev. Lett. 118, 216401 (2017).

  15. 15.

    Zhang, Y., Melko, R. G. & Kim, E.-A. Machine learning 2 quantum spin liquids with quasiparticle statistics. Phys. Rev. B 96, 245119 (2017).

  16. 16.

    van Nieuwenburg, E. P. L., Liu, Y.-H. & Huber, S. D. Learning phase transitions by confusion. Nat. Phys. 13, 435–439 (2017).

  17. 17.

    Ohtsuki, T. & Ohtsuki, T. Deep learning the quantum phase transitions in random two-dimensional electron systems. J. Phys. Soc. Jpn 85, 123706 (2016).

  18. 18.

    Ohtsuki, T. & Ohtsuki, T. Deep learning the quantum phase transitions in random electron systems: applications to three dimensions. J. Phys.Soc. Jpn 86, 044708 (2017).

  19. 19.

    Yoshioka, N., Akagi, Y. & Katsura, H. Learning disordered topological phases by statistical recovery of symmetry. Phys. Rev. B 97, 205110 (2018).

  20. 20.

    Zhang, P., Shen, H. & Zhai, H. Machine learning topological invariants with neural networks. Phys. Rev. Lett. 120, 066401 (2018).

  21. 21.

    Carvalho, D., García-Martínez, N. A., Lado, J. L. & Fernández-Rossier, J. Real-space mapping of topological invariants using artificial neural networks. Phys. Rev. B 97, 115453 (2018).

  22. 22.

    Huembeli, P., Dauphin, A. & Wittek, P. Identifying quantum phase transitions with adversarial neural networks. Phys. Rev. B 97, 134109 (2018).

  23. 23.

    Iakovlev, I. A., Sotnikov, O. M. & Mazurenko, V. V. Supervised learning approach for recognizing magnetic skyrmion phases. Phys. Rev. B 98, 174411 (2018).

  24. 24.

    Vargas-Hernández, R. A., Sous, J., Berciu, M. & Krems, R. V. Extrapolating quantum observables with machine learning: inferring multiple phase transitions from properties of a single phase. Phys. Rev. Lett. 121, 255702 (2018).

  25. 25.

    Beach, M. J. S., Golubeva, A. & Melko, R. G. Machine learning vortices at the Kosterlitz–Thouless transition. Phys. Rev. B 97, 045207 (2018).

  26. 26.

    Wang, C. & Zhai, H. Machine learning of frustrated classical spin models (II): Kernel principal component analysis. Front. Phys. 13, 130507 (2018).

  27. 27.

    Hu, W., Singh, R. R. P. & Scalettar, R. T. Discovering phases, phase transitions and crossovers through unsupervised machine learning: a critical examination. Phys. Rev. E 95, 062122 (2017).

  28. 28.

    Wetzel, S. J. Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders. Phys. Rev. E 96, 022140 (2017).

  29. 29.

    Wang, C. & Zhai, H. Machine learning of frustrated classical spin models. I. Principal component analysis. Phys. Rev. B 96, 144432 (2017).

  30. 30.

    Cristoforetti, M., Jurman, G., Nardelli, A. I. & Furlanello, C. Towards meaningful physics from generative models. Preprint at https://arxiv.org/abs/1705.09524 (2017).

  31. 31.

    Broecker, P., Assaad, F. F. & Trebst, S. Quantum phase recognition via unsupervised machine learning. Preprint at https://arxiv.org/abs/1707.00663 (2017).

  32. 32.

    Zhang, W., Liu, J. & Wei, T.-C. Machine learning of phase transitions in the percolation and XY models. Preprint at https://arxiv.org/abs/1804.02709(2018).

  33. 33.

    Suchsland, P. & Wessel, S. Parameter diagnostics of phases and phase transition learning by neural networks. Phys. Rev. B 97, 174435 (2018).

  34. 34.

    Kosterlitz, J. M. & Thouless, D. J. Ordering, metastability and phase transitions in two-dimensional systems. J. Phys. C 6, 1181 (1973).

  35. 35.

    Sachdev, S. Topological order, emergent gauge fields, and Fermi surface reconstruction. Rep. Prog. Phys. 82, 014001 (2019).

  36. 36.

    Coifman, R. R. et al. Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps. Proc. Natl Acad. Sci USA 102, 7426–7431 (2005).

  37. 37.

    Nadler, B., Lafon, S., Kevrekidis, I. & Coifman, R. R. Diffusion maps, spectral clustering and eigenfunctions of Fokker–Planck operators. In Advances in Neural Information Processing Systems Vol. 18 (eds Weiss, Y., Scholkopf, B. & Platt, J.) 955–962 (MIT Press, 2006).

  38. 38.

    Coifman, R. R. & Lafon, S. Diffusion maps. Appl. Comput. Harmon, Anal. 21, 5–30 (2006).

  39. 39.

    Michalevsky, Y., Talmon, R. & Cohen, I. Speaker identification using diffusion maps. In 19th European Signal Processing Conference, 2011, 1299–1302 (IEEE, 2011).

  40. 40.

    Barkan, O., Weill, J., Wolf, L. & Aronowitz, H. Fast high dimensional vector multiplication face recognition. In Proceedings of the IEEE International Conference on Computer Vision, 1960–1967 (IEEE, 2013).

  41. 41.

    Berezinskii, V. Destruction of long-range order in one-dimensional and two-dimensional systems having a continuous symmetry group I. Classical systems. Sov. Phys. JETP 32, 493–500 (1971).

  42. 42.

    Berezinskii, V. Destruction of long-range order in one-dimensional and two-dimensional systems possessing a continuous symmetry group. II. Quantum systems. Sov. J. Exp. Theor. Phys. 34, 610 (1972).

  43. 43.

    Kosterlitz, J. M. The critical properties of the two-dimensional XY model. J. Phys. C 7, 1046 (1974).

  44. 44.

    Wegner, F. J. Duality in generalized Ising models and phase transitions without local order parameters. J. Math. Phys. 12, 2259–2272 (1971).

  45. 45.

    Kogut, J. B. An introduction to lattice gauge theory and spin systems. Rev. Mod. Phys. 51, 659–713 (1979).

  46. 46.

    Su, W. P., Schrieffer, J. R. & Heeger, A. J. Solitons in polyacetylene. Phys. Rev. Lett. 42, 1698–1701 (1979).

  47. 47.

    Kitaev, A. Y. Unpaired Majorana fermions in quantum wires. Phys.-Uspekhi 44, 131 (2001).

  48. 48.

    Komura, Y. & Okabe, Y. Large-scale Monte Carlo simulation of two-dimensional classical XY model using multiple GPUs. J. Phys. Soc. Jpn 81, 113001 (2012).

Download references

Acknowledgements

The authors thank S. Chatterjee, E. Demler, P.P. Orth, H. Pichler, S. Sachdev, H. Shackleton and Y.-Z. You for useful discussions. J.F.R.-N. acknowledges support from AFOSR-MURI: Photonic Quantum Matter (award FA95501610323). M.S.S. acknowledges support from the German National Academy of Sciences Leopoldina through grant no. LPDS 2016-12 and from the National Science Foundation under grant no. DMR-1664842.

Author information

J.F.R.-N. and M.S.S. contributed equally to the design of the study, performing the simulations, analysis of the results and writing of the manuscript.

Correspondence to Joaquin F. Rodriguez-Nieva or Mathias S. Scheurer.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note: Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Eight figures, three references.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Further reading