Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 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

Numerical approximation of McKean-Vlasov SDEs via stochastic gradient descent (2310.13579v1)

Published 20 Oct 2023 in math.NA, cs.NA, and math.PR

Abstract: We propose a novel approach to numerically approximate McKean-Vlasov stochastic differential equations (MV-SDE) using stochastic gradient descent (SGD) while avoiding the use of interacting particle systems. The technique of SGD is deployed to solve a Euclidean minimization problem, which is obtained by first representing the MV-SDE as a minimization problem over the set of continuous functions of time, and then by approximating the domain with a finite-dimensional subspace. Convergence is established by proving certain intermediate stability and moment estimates of the relevant stochastic processes (including the tangent ones). Numerical experiments illustrate the competitive performance of our SGD based method compared to the IPS benchmarks. This work offers a theoretical foundation for using the SGD method in the context of numerical approximation of MV-SDEs, and provides analytical tools to study its stability and convergence.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. A Fourier-based Picard-iteration approach for a class of McKean-Vlasov SDEs with Lévy jumps. Stochastics 93, 4 (2021), 592–624.
  2. Rate of convergence of a particle method to the solution of the McKean-Vlasov equation. The Annals of Applied Probability 12, 2 (2002), 423–476.
  3. Mean-field description and propagation of chaos in networks of Hodgkin-Huxley and FitzHugh-Nagumo neurons. J. Math. Neurosci. 2 (2012), Art. 10, 50.
  4. An introduction to the numerical analysis of isogeometric methods. In Isogeometric analysis: a new paradigm in the numerical approximation of PDEs, vol. 2161 of Lecture Notes in Math. Springer, [Cham], 2016, pp. 87–154.
  5. Projected particle methods for solving McKean-Vlasov stochastic differential equations. SIAM Journal on Numerical Analysis 56, 6 (2018), 3169–3195.
  6. Gradient convergence in gradient methods with errors. SIAM Journal on Optimization 10, 3 (2000), 627–642.
  7. An explicit Milstein-type scheme for interacting particle systems and McKean–Vlasov SDEs with common noise and non-differentiable drift coefficients. arXiv preprint arXiv:2208.10052 (2022).
  8. A stochastic particle method for the McKean-Vlasov and the Burgers equation. Math. Comp. 66, 217 (1997), 157–192.
  9. Probabilistic Theory of Mean Field Games with Applications I. Springer, 2018.
  10. Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games i: The ergodic case. SIAM Journal on Numerical Analysis 59, 3 (2021), 1455–1485.
  11. Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games: Ii—the finite horizon case. The Annals of Applied Probability 32, 6 (2022), 4065–4105.
  12. A cubature based algorithm to solve decoupled McKean-Vlasov forward-backward stochastic differential equations. Stochastic Processes and their Applications 125, 6 (2015), 2206–2255.
  13. A flexible split-step scheme for solving McKean-Vlasov stochastic differential equations. Appl. Math. Comput. 427 (2022), Paper No. 127180, 23.
  14. Euler simulation of interacting particle systems and McKean–Vlasov SDEs with fully super-linear growth drifts in space and interaction. IMA Journal of Numerical Analysis (05 2023), drad022.
  15. A novel pricing method for European options based on Fourier-cosine series expansions. SIAM J. Sci. Comput. 31, 2 (2008/09), 826–848.
  16. Convergence rates for the stochastic gradient descent method for non-convex objective functions. Journal of Machine Learning Research 21 (2020), 136.
  17. Frank, T. D. Nonlinear Fokker-Planck equations: fundamentals and applications. Springer Science & Business Media, 2005.
  18. Analytical approximations of non-linear SDEs of McKean-Vlasov type. J. Math. Anal. Appl. 466, 1 (2018), 71–106.
  19. Noisy bounded confidence models for opinion dynamics: the effect of boundary conditions on phase transitions. IMA J. Appl. Math. 87, 1 (2022), 80–110.
  20. Multilevel and multi-index Monte Carlo methods for the McKean-Vlasov equation. Statistics and Computing 28, 4 (2018), 923–935.
  21. Solving high-dimensional partial differential equations using deep learning. Proceedings of the National Academy of Sciences 115, 34 (2018), 8505–8510.
  22. Overcoming the curse of dimensionality in the numerical approximation of semilinear parabolic partial differential equations. Proceedings of the Royal Society A 476, 2244 (2020), 20190630.
  23. A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations. SN partial differential equations and applications 1 (2020), 1–34.
  24. Multilevel Picard approximations for McKean-Vlasov stochastic differential equations. J. Math. Anal. Appl. 507, 1 (2022), Paper No. 125761, 14.
  25. Analysis of numerical methods. Courier Corporation, 2012.
  26. Krylov, N. V. Controlled diffusion processes, vol. 14. Springer Science & Business Media, 2008.
  27. Kunita, H. Stochastic differential equations and stochastic flows of diffeomorphisms. In Ecole d’été de probabilités de Saint-Flour XII-1982. Springer, 1984, pp. 143–303.
  28. Méléard, S. Asymptotic behaviour of some interacting particle systems; mckean-vlasov and boltzmann models. In Probabilistic models for nonlinear partial differential equations. Springer, 1996, pp. 42–95.
  29. Stochastic gradient descent on nonconvex functions with general noise models. arXiv preprint arXiv:2104.00423 (2021).
  30. An introduction to numerical analysis. Cambridge University Press, Cambridge, 2003.
  31. Itô-Taylor schemes for solving mean-field stochastic differential equations. Numerical Mathematics: Theory, Methods and Applications 10, 4 (2017), 798–828.
  32. Sznitman, A.-S. Topics in propagation of chaos. In École d’Été de Probabilités de Saint-Flour XIX—1989, vol. 1464 of Lecture Notes in Math. Springer, Berlin, 1991, pp. 165–251.
  33. Iterative particle approximation for McKean-Vlasov SDEs with application to multilevel Monte Carlo estimation. The Annals of Applied Probability 29, 4 (2019), 2230–2265.
  34. A stochastic particle method with random weights for the computation of statistical solutions of McKean-Vlasov equations. The Annals of Applied Probability 13, 1 (2003), 140–180.
  35. Timan, A. F. Theory of approximation of functions of a real variable. Dover Publications, Inc., New York, 1994. Translated from the Russian by J. Berry, Translation edited and with a preface by J. Cossar, Reprint of the 1963 English translation.
Citations (1)
View on Semantic Scholar

Summary

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

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