Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
143 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Exponentially improved efficient machine learning for quantum many-body states with provable guarantees (2304.04353v3)

Published 10 Apr 2023 in quant-ph, cs.LG, and physics.data-an

Abstract: Solving the ground state and the ground-state properties of quantum many-body systems is generically a hard task for classical algorithms. For a family of Hamiltonians defined on an $m$-dimensional space of physical parameters, the ground state and its properties at an arbitrary parameter configuration can be predicted via a machine learning protocol up to a prescribed prediction error $\varepsilon$, provided that a sample set (of size $N$) of the states can be efficiently prepared and measured. In a recent work [Huang et al., Science 377, eabk3333 (2022)], a rigorous guarantee for such a generalization was proved. Unfortunately, an exponential scaling for the provable sample complexity, $N=m{{\cal{O}}\left(\frac{1}{\varepsilon}\right)}$, was found to be universal for generic gapped Hamiltonians. This result applies to the situation where the dimension of the parameter space is large while the scaling with the accuracy is not an urgent factor. In this work, we consider an alternative scenario where $m$ is a finite, not necessarily large constant while the scaling with the prediction error becomes the central concern. By jointly preserving the fundamental properties of density matrices in the learning protocol and utilizing the continuity of quantum states in the parameter range of interest, we rigorously obtain a polynomial sample complexity for predicting quantum many-body states and their properties, with respect to the uniform prediction error $\varepsilon$ and the number of qubits $n$. Moreover, if restricted to learning local quantum-state properties, the number of samples with respect to $n$ can be further reduced exponentially. Our results provide theoretical guarantees for efficient learning of quantum many-body states and their properties, with model-independent applications not restricted to ground states of gapped Hamiltonians.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (115)
  1. G. Carleo and M. Troyer, “Solving the quantum many-body problem with artificial neural networks,” Science 355, 602–606 (2017).
  2. T. Albash and D. A. Lidar, “Adiabatic quantum computation,” Rev. Mod. Phys. 90, 015002 (2018).
  3. I. M. Georgescu, S. Ashhab,  and F. Nori, “Quantum simulation,” Rev. Mod. Phys. 86, 153–185 (2014).
  4. Y. Cao, J. Romero, J. P. Olson, M. Degroote, P. D. Johnson, M. Kieferová, I. D. Kivlichan, T. Menke, B. Peropadre, N. P. D. Sawaya, S. Sim, L. Veis,  and A. Aspuru-Guzik, “Quantum Chemistry in the Age of Quantum Computing,” Chem. Rev. 119, 10856–10915 (2019).
  5. S. Arora and B. Barak, Computational Complexity: A Modern Approach (Cambridge University Press, 2009).
  6. N. Abrahamsen, “Sub-exponential algorithm for 2D frustration-free spin systems with gapped subsystems,” arxiv:2004.02850  (2020).
  7. H.-Y. Huang, R. Kueng, G. Torlai, V. V. Albert,  and J. Preskill, “Provably efficient machine learning for quantum many-body problems,” Science 377, eabk3333 (2022).
  8. M. Schuld, I. Sinayskiy,  and F. Petruccione, “An introduction to quantum machine learning,” Contemp. Phys. 56, 172–185 (2014).
  9. J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe,  and S. Lloyd, “Quantum machine learning,” Nature 549, 195–202 (2017).
  10. V. Dunjko and H. J. Briegel, “Machine learning & artificial intelligence in the quantum domain: a review of recent progress,” Rep. Prog. Phys. 81, 074001 (2018).
  11. G. Carleo, I. Cirac, K. Cranmer, L. Daudet, M. Schuld, N. Tishby, L. Vogt-Maranto,  and L. Zdeborová, “Machine learning and the physical sciences,” Rev. Mod. Phys. 91, 045002 (2019).
  12. P. Mehta, M. Bukov, C.-H. Wang, A. G.R. Day, C. Richardson, C. K. Fisher,  and D. J. Schwab, “A high-bias, low-variance introduction to machine learning for physicists,” Phys. Rep. 810, 1–124 (2019).
  13. X. Gao and L.-M. Duan, ‘‘Efficient representation of quantum many-body states with deep neural networks,” Nat. Commun. 8, 662 (2017).
  14. J. Chen, S. Cheng, H. Xie, L. Wang,  and T. Xiang, “Equivalence of restricted Boltzmann machines and tensor network states,” Phys. Rev. B 97, 085104 (2018).
  15. G. Torlai, G. Mazzola, J. Carrasquilla, M. Troyer, R. Melko,  and G. Carleo, “Neural-network quantum state tomography,” Nat. Phys. 14, 447–450 (2018).
  16. K. Choo, G. Carleo, N. Regnault,  and T. Neupert, “Symmetries and Many-Body Excitations with Neural-Network Quantum States,” Phys. Rev. Lett. 121, 167204 (2018).
  17. J. Gao, L.-F. Qiao, Z.-Q. Jiao, Y.-C. Ma, C.-Q. Hu, R.-J. Ren, A.-L. Yang, H. Tang, M.-H. Yung,  and X.-M. Jin, “Experimental Machine Learning of Quantum States,” Phys. Rev. Lett. 120, 240501 (2018).
  18. F. Noé, S. Olsson, J. Köhler,  and H. Wu, “Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning,” Science 365, eaaw1147 (2019).
  19. N. Yoshioka and R. Hamazaki, “Constructing neural stationary states for open quantum many-body systems,” Phys. Rev. B 99, 214306 (2019).
  20. M. J. Hartmann and G. Carleo, “Neural-Network Approach to Dissipative Quantum Many-Body Dynamics,” Phys. Rev. Lett. 122, 250502 (2019).
  21. A. Nagy and V. Savona, “Variational Quantum Monte Carlo Method with a Neural-Network Ansatz for Open Quantum Systems,” Phys. Rev. Lett. 122, 250501 (2019).
  22. F. Vicentini, A. Biella, N. Regnault,  and C. Ciuti, “Variational Neural-Network Ansatz for Steady States in Open Quantum Systems,” Phys. Rev. Lett. 122, 250503 (2019).
  23. I. A. Luchnikov, A. Ryzhov, P.-J. Stas, S. N. Filippov,  and H. Ouerdane, “Variational autoencoder reconstruction of complex many-body physics,” Entropy 21, 1091 (2019).
  24. K. Cranmer, S. Golkar,  and D. Pappadopulo, “Inferring the quantum density matrix with machine learning,” arXiv:1904.05903  (2019).
  25. H. Y. Kwon, N. J. Kim, C. K. Lee,  and C. Won, “Searching magnetic states using an unsupervised machine learning algorithm with the heisenberg model,” Phys. Rev. B 99, 024423 (2019).
  26. O. Sharir, Y. Levine, N. Wies, G. Carleo,  and A. Shashua, “Deep Autoregressive Models for the Efficient Variational Simulation of Many-Body Quantum Systems,” Phys. Rev. Lett. 124, 020503 (2020).
  27. A. Glielmo, Y. Rath, G. Csányi, A. De Vita,  and G. H. Booth, “Gaussian Process States: A Data-Driven Representation of Quantum Many-Body Physics,” Phys. Rev. X 10, 041026 (2020).
  28. A. Borin and D. A. Abanin, “Approximating power of machine-learning ansatz for quantum many-body states,” Phys. Rev. B 101, 195141 (2020).
  29. C.-Y. Park and M. J. Kastoryano, “Geometry of learning neural quantum states,” Phys. Rev. Res. 2, 023232 (2020).
  30. T. Ohtsuki and T. Mano, “Drawing phase diagrams of random quantum systems by deep learning the wave functions,” J. Phys. Soc. Jpn. 89, 022001 (2020).
  31. R. Zen, L. My, R. Tan, F. Hébert, Ma. Gattobigio, C. Miniatura, D. Poletti,  and S. Bressan, “Transfer learning for scalability of neural-network quantum states,” Phys. Rev. E 101, 053301 (2020).
  32. A. Melkani, C. Gneiting,  and F. Nori, “Eigenstate extraction with neural-network tomography,” Phys. Rev. A 102, 022412 (2020).
  33. A. M. Palmieri, E. Kovlakov, F. Bianchi, D. Yudin, S. Straupe, J. D. Biamonte,  and S. Kulik, “Experimental neural network enhanced quantum tomography,” npj Quantum Information 6, 20 (2020).
  34. S. Lohani, B. T. Kirby, M. Brodsky, O. Danaci,  and R. T. Glasser, “Machine learning assisted quantum state estimation,” Mach. Learn.: Sci. Technol. 1, 035007 (2020).
  35. M. Neugebauer, L. Fischer, A. Jäger, S. Czischek, S. Jochim, M. Weidemüller,  and M. Gärttner, “Neural-network quantum state tomography in a two-qubit experiment,” Phys. Rev. A 102, 042604 (2020).
  36. S. Ahmed, C. Sánchez Muñoz, F. Nori,  and A. F. Kockum, “Quantum State Tomography with Conditional Generative Adversarial Networks,” Phys. Rev. Lett. 127, 140502 (2021a).
  37. S. Ahmed, C. Sánchez Muñoz, F. Nori,  and A. F. Kockum, “Classification and reconstruction of optical quantum states with deep neural networks,” Phys. Rev. Research 3, 033278 (2021b).
  38. J. Yao, L. Lin,  and M. Bukov, “Reinforcement Learning for Many-Body Ground-State Preparation Inspired by Counterdiabatic Driving,” Phys. Rev. X 11, 031070 (2021).
  39. Y. Nomura, N. Yoshioka,  and F. Nori, “Purifying Deep Boltzmann Machines for Thermal Quantum States,” Phys. Rev. Lett. 127, 060601 (2021).
  40. Q. H. Tran and K. Nakajima, “Learning Temporal Quantum Tomography,” Phys. Rev. Lett. 127, 260401 (2021).
  41. P.-L. Zheng, S.-J. Du,  and Y. Zhang, “Ground-state properties via machine learning quantum constraints,” Phys. Rev. Res. 4, L032043 (2022).
  42. A. Anshu and S. Arunachalam, “A survey on the complexity of learning quantum states,” arxiv:2305.20069  (2023).
  43. L. Wang, “Discovering phase transitions with unsupervised learning,” Phys. Rev. B 94, 195105 (2016).
  44. T. Ohtsuki and T. Ohtsuki, “Deep learning the quantum phase transitions in random two-dimensional electron systems,” J. Phys. Soc. Jpn. 85, 123706 (2016).
  45. S. J. Wetzel, “Unsupervised learning of phase transitions: From principal component analysis to variational autoencoders,” Phys. Rev. E 96, 022140 (2017).
  46. P. Broecker, J. Carrasquilla, R. G. Melko,  and S. Trebst, “Machine learning quantum phases of matter beyond the fermion sign problem,” Sci. Rep. 7, 1 (2017).
  47. W. Hu, R. R. P. Singh,  and R. T. Scalettar, “Discovering phases, phase transitions, and crossovers through unsupervised machine learning: A critical examination,” Phys. Rev. E 95, 062122 (2017).
  48. P. Ponte and R. G. Melko, “Kernel methods for interpretable machine learning of order parameters,” Phys. Rev. B 96, 205146 (2017).
  49. J. Carrasquilla and R. G. Melko, “Machine learning phases of matter,” Nat. Phys. 13, 431 (2017).
  50. E. P. L. Van Nieuwenburg, Y.-H. Liu,  and S. D. Huber, “Learning phase transitions by confusion,” Nat. Phys. 13, 435 (2017).
  51. Y. Zhang and E.-A. Kim, “Quantum Loop Topography for Machine Learning,” Phys. Rev. Lett. 118, 216401 (2017).
  52. K. Ch’ng, J. Carrasquilla, R. G. Melko,  and E. Khatami, “Machine learning phases of strongly correlated fermions,” Phys. Rev. X 7, 031038 (2017).
  53. K. Ch’ng, N. Vazquez,  and E. Khatami, “Unsupervised machine learning account of magnetic transitions in the Hubbard model,” Phys. Rev. E 97, 013306 (2018).
  54. M. J. S. Beach, A. Golubeva,  and R. G. Melko, “Machine learning vortices at the Kosterlitz-Thouless transition,” Phys. Rev. B 97, 045207 (2018).
  55. W.-J. Rao, Z. Li, Q. Zhu, M. Luo,  and X. Wan, “Identifying product order with restricted Boltzmann machines,” Phys. Rev. B 97, 094207 (2018).
  56. Y.-H. Liu and E. P. L. van Nieuwenburg, “Discriminative Cooperative Networks for Detecting Phase Transitions,” Phys. Rev. Lett. 120, 176401 (2018).
  57. P. Zhang, H. Shen,  and H. Zhai, “Machine Learning Topological Invariants with Neural Networks,” Phys. Rev. Lett. 120, 066401 (2018).
  58. N. Sun, J. Yi, P. Zhang, H. Shen,  and H. Zhai, “Deep learning topological invariants of band insulators,” Phys. Rev. B 98, 085402 (2018).
  59. P. Huembeli, A. Dauphin,  and P. Wittek, “Identifying quantum phase transitions with adversarial neural networks,” Phys. Rev. B 97, 134109 (2018).
  60. N. Yoshioka, Y. Akagi,  and H. Katsura, “Learning disordered topological phases by statistical recovery of symmetry,” Phys. Rev. B 97, 205110 (2018).
  61. L. Pilozzi, F. A. Farrelly, G. Marcucci,  and C. Conti, “Machine learning inverse problem for topological photonics,” Commun. Phys. 1, 1 (2018).
  62. J. Venderley, V. Khemani,  and E.-A. Kim, “Machine Learning Out-of-Equilibrium Phases of Matter,” Phys. Rev. Lett. 120, 257204 (2018).
  63. W. Zhang, J. Liu,  and T.-C. Wei, “Machine learning of phase transitions in the percolation and X⁢Y𝑋𝑌{XY}italic_X italic_Y models,” Phys. Rev. E 99, 032142 (2019).
  64. P. Huembeli, A. Dauphin, P. Wittek,  and C. Gogolin, “Automated discovery of characteristic features of phase transitions in many-body localization,” Phys. Rev. B 99, 104106 (2019).
  65. X.-Y. Dong, F. Pollmann,  and X.-F. Zhang, “Machine learning of quantum phase transitions,” Phys. Rev. B 99, 121104(R) (2019).
  66. B. S. Rem, N. Käming, M. Tarnowski, L. Asteria, N. Fläschner, C. Becker, K. Sengstock,  and C. Weitenberg, “Identifying quantum phase transitions using artificial neural networks on experimental data,” Nat. Phys. 15, 917–920 (2019).
  67. K. Liu, J. Greitemann,  and L. Pollet, “Learning multiple order parameters with interpretable machines,” Phys. Rev. B 99, 104410 (2019).
  68. C. Giannetti, B. Lucini,  and D. Vadacchino, “Machine learning as a universal tool for quantitative investigations of phase transitions,” Nucl. Phys. B 944, 114639 (2019).
  69. A. Canabarro, F. F. Fanchini, A. L. Malvezzi, R. Pereira,  and R. Chaves, “Unveiling phase transitions with machine learning,” Phys. Rev. B 100, 045129 (2019).
  70. F. Schäfer and N. Lörch, “Vector field divergence of predictive model output as indication of phase transitions,” Phys. Rev. E 99, 062107 (2019).
  71. S. Durr and S. Chakravarty, “Unsupervised learning eigenstate phases of matter,” Phys. Rev. B 100, 075102 (2019).
  72. W. Lian, S.-T. Wang, S. Lu, Y. Huang, F. Wang, X. Yuan, W. Zhang, X. Ouyang, X. Wang, X. Huang, L. He, X. Chang, D.-L. Deng,  and L. Duan, “Machine Learning Topological Phases with a Solid-State Quantum Simulator,” Phys. Rev. Lett. 122, 210503 (2019).
  73. J. F. Rodriguez-Nieva and M. S. Scheurer, “Identifying topological order through unsupervised machine learning,” Nat. Phys. 15, 790–795 (2019).
  74. Y. Che, C. Gneiting, T. Liu,  and F. Nori, “Topological quantum phase transitions retrieved through unsupervised machine learning,” Phys. Rev. B 102, 134213 (2020).
  75. M. S. Scheurer and R.-J. Slager, “Unsupervised Machine Learning and Band Topology,” Phys. Rev. Lett. 124, 226401 (2020).
  76. Y. Long, J. Ren,  and H. Chen, “Unsupervised Manifold Clustering of Topological Phononics,” Phys. Rev. Lett. 124, 185501 (2020).
  77. A. Lidiak and Z. Gong, “Unsupervised Machine Learning of Quantum Phase Transitions Using Diffusion Maps,” Phys. Rev. Lett. 125, 225701 (2020).
  78. O. Balabanov and M. Granath, “Unsupervised learning using topological data augmentation,” Phys. Rev. Research 2, 013354 (2020).
  79. E. Greplova, A. Valenti, G. Boschung, F. Schäfer, N. Lörch,  and S. D. Huber, “Unsupervised identification of topological phase transitions using predictive models,” New Journal of Physics 22, 045003 (2020).
  80. A. Berezutskii, M. Beketov, D. Yudin, Z. Zimborás,  and J. D. Biamonte, “Probing criticality in quantum spin chains with neural networks,” Journal of Physics: Complexity 1, 03LT01 (2020).
  81. L.-W. Yu and D.-L. Deng, “Unsupervised Learning of Non-Hermitian Topological Phases,” Phys. Rev. Lett. 126, 240402 (2021).
  82. T. Mendes-Santos, X. Turkeshi, M. Dalmonte,  and A. Rodriguez, “Unsupervised learning universal critical behavior via the intrinsic dimension,” Phys. Rev. X 11, 011040 (2021a).
  83. T. Mendes-Santos, A. Angelone, A. Rodriguez, R. Fazio,  and M. Dalmonte, “Intrinsic dimension of path integrals: Data-mining quantum criticality and emergent simplicity,” PRX Quantum 2, 030332 (2021b).
  84. Y. Long and B. Zhang, “Unsupervised Data-Driven Classification of Topological Gapped Systems with Symmetries,” Phys. Rev. Lett. 130, 036601 (2023).
  85. H.-Y. Huang, R. Kueng,  and J. Preskill, “Predicting many properties of a quantum system from very few measurements,” Nat. Phys. 16, 1050–1057 (2020).
  86. H.-Y. Huang, R. Kueng,  and J. Preskill, “Efficient Estimation of Pauli Observables by Derandomization,” Phys. Rev. Lett. 127, 030503 (2021).
  87. L. G. Valiant, “A theory of the learnable,” Communications of the ACM 27, 1134–1142 (1984).
  88. E. M. Stein and R. Shakarchi, Fourier Analysis: An Introduction (Princeton University Press, 2003).
  89. I. Steinwart and A. Christmann, Support Vector Machines (Springer Publishing Company, Incorporated, 2008).
  90. R. R. Coifman, S. Lafon, A. B. Lee, M. Maggioni, B. Nadler, F. Warner,  and S. W. Zucker, “Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps,” Proc. Natl. Acad. Sci. U.S.A. 102, 7426–7431 (2005).
  91. B. Nadler, S. Lafon, I. Kevrekidis,  and R. R. Coifman, “Diffusion maps, spectral clustering and eigenfunctions of Fokker-Planck operators,” in Advances in neural information processing systems (2006) pp. 955–962.
  92. R. Chatterjee and T. Yu, “Generalized coherent states, reproducing kernels, and quantum support vector machines,” Quantum Inf. Commun. 17, 1292 (2017).
  93. K. Bartkiewicz, C. Gneiting, A. Černoch, K. Jiráková, K. Lemr,  and F. Nori, “Experimental kernel-based quantum machine learning in finite feature space,” Sci. Rep. 10, 12356 (2020).
  94. A. Jacot, F. Gabriel,  and C. Hongler, “Neural tangent kernel: Convergence and generalization in neural networks,” in Advances in Neural Information Processing Systems, Vol. 31, edited by S. Bengio et. al. (Curran Associates, Inc., 2018) pp. 8571–8580.
  95. H. Q. Minh, L. Bazzani,  and V. Murino, “A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning,” Journal of Machine Learning Research 17, 1–72 (2016).
  96. M. Schuld, “Supervised quantum machine learning models are kernel methods,” arxiv:2101.11020  (2021).
  97. D. Gross, Y.-K. Liu, S. T. Flammia, S. Becker,  and J. Eisert, “Quantum State Tomography via Compressed Sensing,” Phys. Rev. Lett. 105, 150401 (2010).
  98. For a more detailed introduction of the classical shadow tomography, see the supplemental material of Ref. Huang et al. (2022).
  99. See the supplemental material.
  100. L. Pfister and Y. Bresler, “Bounding multivariate trigonometric polynomials,” IEEE Transactions on Signal Processing 67, 700–707 (2019).
  101. S. Sachdev, Quantum Phase Transitions (Cambridge University Press, 2011).
  102. A. De Pasquale and P. Facchi, “X⁢Y𝑋𝑌XYitalic_X italic_Y model on the circle: Diagonalization, spectrum, and forerunners of the quantum phase transition,” Phys. Rev. A 80, 032102 (2009).
  103. M. Okuyama, Y. Yamanaka, H. Nishimori,  and M. M. Rams, “Anomalous behavior of the energy gap in the one-dimensional quantum X⁢Y𝑋𝑌XYitalic_X italic_Y model,” Phys. Rev. E 92, 052116 (2015).
  104. P. Jordan and E. Wigner, “Über das Paulische Äquivalenzverbot,” Z. Phys. 47, 631–651 (1928).
  105. S. B. Bravyi and A. Y. Kitaev, “Fermionic Quantum Computation,” Ann. Phys. 298, 210–226 (2002).
  106. There are two additional but not obvious points in the vicinity of h/J=±1ℎ𝐽plus-or-minus1h/J=\pm 1italic_h / italic_J = ± 1 where the energy curve is continuous but not smooth due to the vacua competition, which are not indicated in this figure.
  107. E. Barouch and B. M. McCoy, “Statistical Mechanics of the X⁢Y𝑋𝑌XYitalic_X italic_Y Model. II. Spin-Correlation Functions,” Phys. Rev. A 3, 786–804 (1971).
  108. E. Onorati, C. Rouzé, D. S. França,  and J. D. Watson, “Efficient learning of ground & thermal states within phases of matter,” arxiv:2301.12946  (2023).
  109. L. Lewis, H.-Y. Huang, V. T. Tran, S. Lehner, R. Kueng,  and J. Preskill, “Improved machine learning algorithm for predicting ground state properties,” arxiv:2301.13169  (2023).
  110. This is guaranteed by the Heine-Cantor theorem which states that a continuous function defined on a compact metric space is uniformly continuous. Here the input space 𝒳𝒳{\cal{X}}caligraphic_X is a compact metric space.
  111. S. Bachmann, S. Michalakis, B. Nachtergaele,  and R. Sims, “Automorphic Equivalence within Gapped Phases of Quantum Lattice Systems,” Commun. Math. Phys. 309, 835–871 (2012).
  112. M. A. Nielsen and I. L. Chuang, Quantum Computation and Quantum Information (Cambridge University Press, Cambridge, England, 2012).
  113. J. Liu, H. Yuan, X.-M. Lu,  and X. Wang, “Quantum Fisher information matrix and multiparameter estimation,” J. Phys. A: Math. Theor. 53, 023001 (2020).
  114. C. W. Helstrom, Quantum Detection and Estimation Theory (Academic Press, New York, 1976).
  115. A. S. Holevo, Probabilistic and Statistical Aspects of Quantum Theory (North-Holland Publishing Company, Amsterdam, 1982).
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now