Abstract
The authors present a novel deep learning method for computing eigenvalues of the fractional Schrödinger operator. The proposed approach combines a newly developed loss function with an innovative neural network architecture that incorporates prior knowledge of the problem. These improvements enable the proposed method to handle both high-dimensional problems and problems posed on irregular bounded domains. The authors successfully compute up to the first 30 eigenvalues for various fractional Schrödinger operators. As an application, the authors share a conjecture to the fractional order isospectral problem that has not yet been studied.
Similar content being viewed by others
References
Metzler R and Klafter J, The random walk’s guide to anomalous diffusion: A fractional dynamics approach, Physics Reports, 2000, 339(1): 1–77.
Shlesinger M F, West B J, and Klafter J, Lévy dynamics of enhanced diffusion: Application to turbulence, Physical Review Letters, 1987, 58(11): 1100–1103.
de Pablo A, Quirós F, Rodríguez A, et al., A fractional porous medium equation, Advances in Mathematics, 2011, 226(2): 1378–1409.
Laskin N, Fractional quantum mechanics and Lévy path integrals, Physics Letters A, 2000, 268(4–6): 298–305.
Laskin N, Fractional Schrödinger equation, Physical Review E, 2002, 66(5): 056108.
Longhi S, Fractional Schrödinger equation in optics, Optics Letters, 2015, 40(6): 1117–1120.
Zhang Y, Zhong H, Belić M R, et al., PT symmetry in a fractional Schrödinger equation, Laser & Photonics Reviews, 2016, 10(3): 526–531.
Ainsworth M and Glusa C, Aspects of an adaptive finite element method for the fractional Laplacian: A priori and a posteriori error estimates, efficient implementation and multigrid solver, Computer Methods in Applied Mechanics and Engineering, 2017, 327: 4–35.
Ainsworth M and Glusa C, Towards an efficient finite element method for the integral fractional Laplacian on polygonal domains, Contemporary Computational Mathematics — A Celebration of the 80th Birthday of Ian Sloan, Eds. by Dick J, Kuo F Y, and Woźniakowski H, Springer, Cham, 2018.
Del Teso F, Endal J, and Jakobsen E R, Robust numerical methods for nonlocal (and local) equations of porous medium type, Part II: Schemes and experiments, SIAM Journal on Numerical Analysis, 2018, 56(6): 3611–3647.
Mao Z, Chen S, and Shen J, Efficient and accurate spectral method using generalized Jacobi functions for solving Riesz fractional differential equations, Applied Numerical Mathematics, 2016, 106: 165–181.
Kyprianou A E, Osojnik A, and Shardlow T, Unbiased ‘walk-on-spheres’ Monte Carlo methods for the fractional Laplacian, IMA Journal of Numerical Analysis, 2018, 38(3): 1550–1578.
Shardlow T, A walk outside spheres for the fractional Laplacian: Fields and first eigenvalue, Mathematics of Computation, 2019, 88(320): 2767–2792.
D’Elia M, Du Q, Glusa C, et al., Numerical methods for nonlocal and fractional models, Acta Numerica, 2020, 29: 1–124.
Lischke A, Pang G, Gulian M, et al., What is the fractional Laplacian? A comparative review with new results, Journal of Computational Physics, 2020, 404: 109009.
Bonito A, Borthagaray J P, Nochetto R H, et al., Numerical methods for fractional diffusion, Computing and Visualization in Science, 2018, 19: 19–46.
Dyda B, Kuznetsov A, and Kwaśnicki M, Eigenvalues of the fractional Laplace operator in the unit ball, Journal of the London Mathematical Society, 2017, 95(2): 500–518.
Dyda B, Fractional calculus for power functions and eigenvalues of the fractional Laplacian, Fractional Calculus and Applied Analysis, 2012, 15(4): 536–555.
Bao W, Chen L, Jiang X, et al., A Jacobi spectral method for computing eigenvalue gaps and their distribution statistics of the fractional Schrödinger operator, Journal of Computational Physics, 2020, 421: 109733.
Borthagaray J P, Del Pezzo L M, and Martínez S, Finite element approximation for the fractional eigenvalue problem, Journal of Scientific Computing, 2018, 77(1): 308–329.
Samardzija N and Waterland R L, A neural network for computing eigenvectors and eigenvalues, Biological Cybernetics, 1991, 65(4): 211–214.
Cichocki A and Unbehauen R, Neural networks for computing eigenvalues and eigenvectors, Biological Cybernetics, 1992, 68: 155–164.
Carleo G and Troyer M, Solving the quantum many-body problem with artificial neural networks, Science, 2017, 355(6325): 602–606.
Choo K, Mezzacapo A, and Carleo G, Fermionic neural-network states for ab-initio electronic structure, Nature Communications, 2020, 11(1): 2368.
Han J, Zhang L, and E W, Solving many-electron Schrödinger equation using deep neural networks, Journal of Computational Physics, 2019, 399: 108929.
Han J, Lu J, and Zhou M, Solving high-dimensional eigenvalue problems using deep neural networks: A diffusion Monte Carlo like approach, Journal of Computational Physics, 2020, 423: 109792.
Li H and Ying L, A semigroup method for high dimensional elliptic PDEs and eigenvalue problems based on neural networks, Journal of Computational Physics, 2022, 453: 110939.
Zhang W, Li T, and Schütte C, Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks, Journal of Computational Physics, 2022, 465: 111377.
Elhamod M, Bu J, Singh C, et al., CoPhy-PGNN: Learning physics-guided neural networks with competing loss functions for solving eigenvalue problems, ACM Transactions on Intelligent Systems and Technology, 2022, 13(6): 1–23.
Finol D, Lu Y, Mahadevan V, et al., Deep convolutional neural networks for eigenvalue problems in mechanics, International Journal for Numerical Methods in Engineering, 2019, 118(5): 258–275.
Lu J and Lu Y, A priori generalization error analysis of two-layer neural networks for solving high dimensional Schrödinger eigenvalue problems, Communications of the American Mathematical Society, 2022, 2(1): 1–21.
Kwaśnicki M, Ten equivalent definitions of the fractional Laplace operator, Fractional Calculus and Applied Analysis, 2017, 20(1): 7–51.
Valdinoci E, From the long jump random walk to the fractional Laplacian, Bulletin of the Spanish Society of Applied Mathematics, 2009, 49: 33–44.
Frank R L, Eigenvalue bounds for the fractional Laplacian: A review, Recent Developments in Nonlocal Theory, Eds. by Palatucci G and Kuusi T, Walter de Gruyter, Berlin, 2017, 210–235.
Chen Z Q and Song R, Two-sided eigenvalue estimates for subordinate processes in domains, Journal of Functional Analysis, 2005, 226(1): 90–113.
Bao W, Ruan X, Shen J, et al., Fundamental gaps of the fractional Schrödinger operator, Communications in Mathematical Sciences, 2019, 17(2): 447–471.
Grubb G, Fractional Laplacians on domains, a development of Hörmander’s theory of μ-transmission pseudodifferential operators, Advances in Mathematics, 2015, 268: 478–528.
Khoo Y, Lu J, and Ying L. Solving for high-dimensional committor functions using artificial neural networks, Research in the Mathematical Sciences, 2019, 6: 1–13.
Liu X and Oishi S, Verified eigenvalue evaluation for the Laplacian over polygonal domains of arbitrary shape, SIAM Journal on Numerical Analysis, 2013, 51(3): 1634–1654.
Yuan Q and He Z, Bounds to eigenvalues of the Laplacian on L-shaped domain by variational methods, Journal of Computational and Applied Mathematics, 2009, 233(4): 1083–1090.
Kac M, Can one hear the shape of a drum? The American Mathematical Monthly, 1966, 73(492): 1–33.
Gordon C, Webb D L, and Wolpert S, One cannot hear the shape of a drum, Bulletin of the American Mathematical Society, 1992, 27(1): 134–138.
Gordon C, Webb D L, and Wolpert S, Isospectral plane domains and surfaces via Riemannian orbifolds, Inventiones Mathematicae, 1992, 110(1): 1–22.
Driscoll T A, Eigenmodes of isospectral drums, SIAM Review, 1997, 39(1): 1–17.
Borzì A and Borzì G, Algebraic multigrid methods for solving generalized eigenvalue problems, International Journal for Numerical Methods in Engineering, 2006, 65(8): 1186–1196.
Li H and Zhang Z, Efficient spectral and spectral element methods for eigenvalue problems of Schrödinger equations with an inverse square potential, SIAM Journal on Scientific Computing, 2017, 39(1): A114–A140.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare no conflict of interest.
Additional information
This work was supported by the National Natural Science Foundation of China under Grant Nos. 12371438 and 12326336.
Rights and permissions
About this article
Cite this article
Guo, Y., Ming, P. A Deep Learning Method for Computing Eigenvalues of the Fractional Schrödinger Operator. J Syst Sci Complex 37, 391–412 (2024). https://doi.org/10.1007/s11424-024-3250-9
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11424-024-3250-9