Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
149 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations (2303.02304v4)

Published 4 Mar 2023 in cs.LG

Abstract: Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes. Recently, neural operators have shown the ability to solve PDEs by learning the integral kernel directly in Fourier/Wavelet space, so the difficulty for solving the coupled PDEs depends on dealing with the coupled mappings between the functions. Towards this end, we propose a \textit{coupled multiwavelets neural operator} (CMWNO) learning scheme by decoupling the coupled integral kernels during the multiwavelet decomposition and reconstruction procedures in the Wavelet space. The proposed model achieves significantly higher accuracy compared to previous learning-based solvers in solving the coupled PDEs including Gray-Scott (GS) equations and the non-local mean field game (MFG) problem. According to our experimental results, the proposed model exhibits a $2\times \sim 4\times$ improvement relative $L$2 error compared to the best results from the state-of-the-art models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Mean field games: numerical methods. SIAM Journal on Numerical Analysis, 48(3):1136–1162, 2010.
  2. Hamilton-jacobi equations: approximations, numerical analysis and applications. 2013a.
  3. Mean field games: convergence of a finite difference method. SIAM Journal on Numerical Analysis, 51(5):2585–2612, 2013b.
  4. Partial differential equation models in macroeconomics. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 372(2028):20130397, 2014.
  5. Income and wealth distribution in macroeconomics: A continuous-time approach. The review of economic studies, 89(1):45–86, 2022.
  6. Adaptive solution of partial differential equations in multiwavelet bases. Journal of Computational Physics, 182(1):149–190, 2002a. ISSN 0021-9991.
  7. Adaptive solution of partial differential equations in multiwavelet bases. Journal of Computational Physics, 182(1):149–190, 2002b.
  8. Wavelet-like bases for the fast solution of second-kind integral equations. SIAM journal on Scientific Computing, 14(1):159–184, 1993.
  9. Bradley K. Alpert. A class of bases in L2superscript𝐿2{L}^{2}italic_L start_POSTSUPERSCRIPT 2 end_POSTSUPERSCRIPT for the sparse representation of integral operators. SIAM Journal on Mathematical Analysis, 24(1):246–262, 1993a. doi: 10.1137/0524016.
  10. Bradley K Alpert. A class of bases in l^2 for the sparse representation of integral operators. SIAM journal on Mathematical Analysis, 24(1):246–262, 1993b.
  11. Augmented lagrangian methods for transport optimization, mean field games and degenerate elliptic equations. Journal of Optimization Theory and Applications, 167(1):1–26, 2015.
  12. Variational mean field games. In Active Particles, Volume 1, pp.  141–171. Springer, 2017.
  13. Scheduled sampling for sequence prediction with recurrent neural networks. Advances in neural information processing systems, 28, 2015.
  14. Fast wavelet transforms and numerical algorithms i. Communications on pure and applied mathematics, 44(2):141–183, 1991.
  15. Model reduction and neural networks for parametric pdes, 2020.
  16. Diagnostic model and analysis of the surface currents in the tropical pacific ocean. Journal of Physical Oceanography, 32(10):2938–2954, 2002.
  17. On the implementation of a primal-dual algorithm for second order time-dependent mean field games with local couplings. ESAIM: Proceedings and Surveys, 65:330–348, 2019.
  18. Proximal methods for stationary mean field games with local couplings. SIAM Journal on Control and Optimization, 56(2):801–836, 2018.
  19. Spectral temporal graph neural network for multivariate time-series forecasting. Advances in neural information processing systems, 33:17766–17778, 2020.
  20. Spectral temporal graph neural network for trajectory prediction. In 2021 IEEE International Conference on Robotics and Automation (ICRA), pp.  1839–1845. IEEE, 2021.
  21. A synthetic limit order book dataset for benchmarking forecasting algorithms under distributional shift. In NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 2022. URL https://openreview.net/forum?id=_u-1--wBV1.
  22. Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems. IEEE Transactions on Neural Networks, 6(4):911–917, 1995.
  23. Partitioned time stepping for a parabolic two domain problem. SIAM Journal on Numerical Analysis, 47(5):3526–3549, 2009. doi: 10.1137/080740891. URL https://doi.org/10.1137/080740891.
  24. Exponential time differencing for stiff systems. Journal of Computational Physics, 176(2):430–455, 2002.
  25. A mean field game approach for distributed control of thermostatic loads acting in simultaneous energy-frequency response markets. IEEE Transactions on Smart Grid, 10(6):5987–5999, 2019.
  26. Chebfun Guide. Pafnuty Publications, 2014.
  27. Analysis of automotive cyber-attacks on highways using partial differential equation models. IEEE Transactions on Control of Network Systems, 5(4):1775–1786, 2017.
  28. Elliptic partial differential equations of second order, volume 224. Springer, 1977.
  29. One-dimensional, forward-forward mean-field games with congestion. arXiv preprint arXiv:1703.10029, 2017.
  30. Diogo A Gomes et al. A mean-field game approach to price formation. Dynamic Games and Applications, 11(1):29–53, 2021.
  31. Physics-informed neural operators. arXiv preprint arXiv:2207.05748, 2022.
  32. Mean field games and applications. In Paris-Princeton lectures on mathematical finance 2010, pp. 205–266. Springer, 2011.
  33. Non-linear operator approximations for initial value problems. In International Conference on Learning Representations, 2021a.
  34. Multiwavelet-based operator learning for differential equations, 2021b.
  35. Craig S Henriquez. Simulating the electrical behavior of cardiac tissue using the bidomain model. Critical reviews in biomedical engineering, 21(1):1–77, 1993.
  36. Large population stochastic dynamic games: closed-loop mckean-vlasov systems and the nash certainty equivalence principle. Communications in Information & Systems, 6(3):221–252, 2006.
  37. Large-population cost-coupled lqg problems with nonuniform agents: Individual-mass behavior and decentralized ε𝜀\varepsilonitalic_ε-nash equilibria. IEEE Transactions on Automatic Control, 52(9):1560–1571, 2007. doi: 10.1109/TAC.2007.904450.
  38. Mean-field game strategies for optimal execution. Applied Mathematical Finance, 26(2):153–185, 2019.
  39. Neural operator: Learning maps between function spaces. arXiv preprint arXiv:2108.08481, 2021.
  40. Mechanical hemolysis in blood flow: user-independent predictions with the solution of a partial differential equation. Computer Methods in Biomechanics and Biomedical Engineering, 10(1):1–12, 2007.
  41. Jeux à champ moyen. i–le cas stationnaire. Comptes Rendus Mathématique, 343(9):619–625, 2006.
  42. Mean field games. Japanese journal of mathematics, 2(1):229–260, 2007.
  43. The hamilton–jacobi partial differential equation and the three representations of traffic flow. Transportation Research Part B: Methodological, 52:17–30, 2013.
  44. Fourier neural operator for parametric partial differential equations, 2020a.
  45. Neural operator: Graph kernel network for partial differential equations, 2020b.
  46. Multipole graph neural operator for parametric partial differential equations. In Advances in Neural Information Processing Systems, volume 33, pp.  6755–6766, 2020c.
  47. Splitting methods for a class of non-potential mean field games. arXiv preprint arXiv:2007.00099, 2020.
  48. Computational methods for first-order nonlocal mean field games with applications. SIAM Journal on Numerical Analysis, 59(5):2639–2668, 2021.
  49. Learning nonlinear operators via deeponet based on the universal approximation theorem of operators. Nature Machine Intelligence, 3(3):218–229, 2021.
  50. A comprehensive and fair comparison of two neural operators (with practical extensions) based on fair data. Computer Methods in Applied Mechanics and Engineering, 393:114778, 2022.
  51. When physics meets machine learning: A survey of physics-informed machine learning. arXiv preprint arXiv:2203.16797, 2022.
  52. Rectified linear units improve restricted boltzmann machines. In Icml, 2010.
  53. A physics-informed operator regression framework for extracting data-driven continuum models. Computer Methods in Applied Mechanics and Engineering, 373:113500, 2021. ISSN 0045-7825. doi: https://doi.org/10.1016/j.cma.2020.113500.
  54. Fourcastnet: A global data-driven high-resolution weather model using adaptive fourier neural operators. arXiv preprint arXiv:2202.11214, 2022.
  55. Partial differential equation-based trajectory planning for multiple unmanned air vehicles in dynamic and uncertain environments. Journal of Dynamic Systems, Measurement, and Control, 142(4), 2020.
  56. Learned coarse models for efficient turbulence simulation. arXiv preprint arXiv:2112.15275, 2021.
  57. The oriented-couple partial differential equations for filtering in wrapped phase patterns. Optics Express, 17(7):5606–5617, 2009.
  58. U-fno—an enhanced fourier neural operator-based deep-learning model for multiphase flow. Advances in Water Resources, 163:104180, 2022.
  59. Deciphering the generating rules and functionalities of complex networks. Scientific reports, 11(1):22964, 2021.
  60. Constructing compact causal mathematical models for complex dynamics. In 2017 ACM/IEEE 8th International Conference on Cyber-Physical Systems (ICCPS), pp.  97–108, April 2017.
  61. Network science characteristics of brain-derived neuronal cultures deciphered from quantitative phase imaging data. Scientific reports, 10(1):15078, 2020.
  62. Counterfactual neural temporal point process for estimating causal influence of misinformation on social media. In Advances in Neural Information Processing Systems, 2022.
Citations (9)
View on Semantic Scholar

Summary

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

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