{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T18:12:38Z","timestamp":1776363158524,"version":"3.51.2"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sci Comput"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We introduce the deep multi-FBSDE method for robust approximation of coupled forward-backward stochastic differential equations (FBSDEs), focusing on cases where the deep BSDE method of Han, Jentzen, and E (2018) fails to converge. To overcome the convergence issues, we consider a family of FBSDEs that are equivalent to the original problem in the sense that they satisfy the same associated partial differential equation (PDE) and initial value. Our algorithm proceeds in two phases: first, we approximate the initial condition jointly for a small number of FBSDEs from the FBSDE family, and second, we approximate the original FBSDE using the initial condition approximated in the first phase. Numerical experiments show that our method converges even when the standard deep FBSDE method does not.<\/jats:p>","DOI":"10.1007\/s10915-026-03202-1","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T03:37:24Z","timestamp":1770608244000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The Deep Multi-FBSDE Method: A Robust Deep Learning Method for Coupled FBSDEs"],"prefix":"10.1007","volume":"106","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7186-4840","authenticated-orcid":false,"given":"Kristoffer","family":"Andersson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Andersson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelis W.","family":"Oosterlee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"issue":"1","key":"3202_CR1","doi-asserted-by":"publisher","first-page":"A226","DOI":"10.1137\/22M1478057","volume":"45","author":"K Andersson","year":"2023","unstructured":"Andersson, K., Andersson, A., Oosterlee, C.W.: Convergence of a robust deep FBSDE method for stochastic control. SIAM J. Sci. Comput. 45(1), A226\u2013A255 (2023)","journal-title":"SIAM J. Sci. Comput."},{"key":"3202_CR2","doi-asserted-by":"crossref","unstructured":"Andersson, K., Gnoatto, A.: Multi-layer Deep xVA: Structural Credit Models, Measure Changes and Convergence Analysis. arXiv preprint arXiv:2502.14766 (2025)","DOI":"10.2139\/ssrn.5147413"},{"issue":"3","key":"3202_CR3","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1137\/23M1615048","volume":"16","author":"K Andersson","year":"2025","unstructured":"Andersson, K., Gnoatto, A., Patacca, M., Picarelli, A.: A deep solver for BSDEs with jumps. SIAM J. Financ. Math. 16(3), 875\u2013911 (2025)","journal-title":"SIAM J. Financ. Math."},{"key":"3202_CR4","unstructured":"\u00c5str\u00f6m, K.J.: Introduction to stochastic control theory. Courier Corporation (2012)"},{"issue":"5","key":"3202_CR5","doi-asserted-by":"publisher","first-page":"A3135","DOI":"10.1137\/19M1297919","volume":"43","author":"C Beck","year":"2021","unstructured":"Beck, C., Becker, S., Cheridito, P., Jentzen, A., Neufeld, A.: Deep splitting method for parabolic PDEs. SIAM J. Sci. Comput. 43(5), A3135\u2013A3154 (2021)","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"3202_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10915-021-01590-0","volume":"88","author":"C Beck","year":"2021","unstructured":"Beck, C., Becker, S., Grohs, P., Jaafari, N., Jentzen, A.: Solving the Kolmogorov PDE by means of deep learning. J. Sci. Comput. 88(3), 1\u201328 (2021)","journal-title":"J. Sci. Comput."},{"key":"3202_CR7","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1007\/s00332-018-9525-3","volume":"29","author":"C Beck","year":"2019","unstructured":"Beck, C., Weinan, E., Jentzen, A.: Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations. J. Nonlinear Sci. 29, 1563\u20131619 (2019)","journal-title":"J. Nonlinear Sci."},{"issue":"6","key":"3202_CR8","doi-asserted-by":"publisher","first-page":"3697","DOI":"10.3934\/dcdsb.2022238","volume":"28","author":"C Beck","year":"2023","unstructured":"Beck, C., Hutzenthaler, M., Jentzen, A., Kuckuck, B.: An overview on deep learning-based approximation methods for partial differential equations. Discrete Continuous Dyn. Syst. \u2013 Series B 28(6), 3697\u20133746 (2023). https:\/\/doi.org\/10.3934\/dcdsb.2022238","journal-title":"Discrete Continuous Dyn. Syst. \u2013 Series B"},{"issue":"1","key":"3202_CR9","first-page":"143","volume":"18","author":"C Bender","year":"2008","unstructured":"Bender, C., Zhang, J.: Time discretization and markovian iteration for coupled fbsdes. Annal. Appl. Probab 18(1), 143\u2013177 (2008)","journal-title":"Annal. Appl. Probab"},{"issue":"3","key":"3202_CR10","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1137\/19M125649X","volume":"2","author":"J Berner","year":"2020","unstructured":"Berner, J., Grohs, P., Jentzen, A.: Analysis of the generalization error: Empirical risk minimization over deep artificial neural networks overcomes the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations. SIAM J. Math. Data Sci. 2(3), 631\u2013657 (2020)","journal-title":"SIAM J. Math. Data Sci."},{"key":"3202_CR11","unstructured":"Bussell, D., Garc\u00eda-Trillos, C.A.: Deep multi-step mixed algorithm for high dimensional non-linear PDEs and associated BSDEs. arXiv preprint arXiv:2308.14487 (2023)"},{"key":"3202_CR12","doi-asserted-by":"crossref","unstructured":"Cai, W., Fang, S., Zhou, T.: Deep random difference method for high dimensional quasilinear parabolic partial differential equations. arXiv preprint arXiv:2506.20308 (2025)","DOI":"10.2139\/ssrn.5388712"},{"issue":"4","key":"3202_CR13","doi-asserted-by":"publisher","first-page":"C795","DOI":"10.1137\/24M1681033","volume":"47","author":"W Cai","year":"2025","unstructured":"Cai, W., Fang, S., Zhou, T.: SOC-MartNet: A Martingale Neural Network for the Hamilton-Jacobi-Bellman Equation Without Explicit inf H in Stochastic Optimal Controls. SIAM J. Sci. Comput. 47(4), C795\u2013C819 (2025)","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"3202_CR14","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.1007\/s10915-019-00908-3","volume":"79","author":"Q Chan-Wai-Nam","year":"2019","unstructured":"Chan-Wai-Nam, Q., Mikael, J., Warin, X.: Machine learning for semi linear PDEs. J. Sci. Comput. 79(3), 1667\u20131712 (2019)","journal-title":"J. Sci. Comput."},{"key":"3202_CR15","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1214\/23-PS18","volume":"20","author":"J Chessari","year":"2023","unstructured":"Chessari, J., Kawai, R., Shinozaki, Y., Yamada, T.: Numerical methods for backward stochastic differential equations: A survey. Probab. Surv. 20, 486\u2013567 (2023)","journal-title":"Probab. Surv."},{"key":"3202_CR16","doi-asserted-by":"crossref","unstructured":"Elbr\u00e4chter, D., Grohs, P., Jentzen, A., Schwab, C.: DNN expression rate analysis of high-dimensional PDEs: Application to option pricing. Constructive Approximation pp. 1\u201369 (2021)","DOI":"10.1007\/s00365-021-09541-6"},{"issue":"2","key":"3202_CR17","doi-asserted-by":"publisher","first-page":"826","DOI":"10.1137\/080718061","volume":"31","author":"F Fang","year":"2009","unstructured":"Fang, F., Oosterlee, C.W.: A novel pricing method for european options based on fourier-cosine series expansions. SIAM J. Sci. Comput. 31(2), 826\u2013848 (2009)","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"3202_CR18","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s10690-019-09271-7","volume":"26","author":"M Fujii","year":"2019","unstructured":"Fujii, M., Takahashi, A., Takahashi, M.: Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs. Asia-Pacific Finan. Markets. 26(3), 391\u2013408 (2019)","journal-title":"Asia-Pacific Finan. Markets."},{"issue":"1","key":"3202_CR19","doi-asserted-by":"publisher","first-page":"A28","DOI":"10.1137\/20M1355355","volume":"44","author":"M Germain","year":"2022","unstructured":"Germain, M., Pham, H., Warin, X.: Approximation error analysis of some deep backward schemes for nonlinear PDEs. SIAM J. Sci. Comput. 44(1), A28\u2013A56 (2022)","journal-title":"SIAM J. Sci. Comput."},{"key":"3202_CR20","doi-asserted-by":"publisher","unstructured":"Grohs, P., Hornung, F., Jentzen, A., von Wurstemberger, P.: A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black\u2013Scholes partial differential equations, Memoirs of the American Mathematical Society, vol. 284 (1410). American Mathematical Society, Providence, RI (2023). https:\/\/doi.org\/10.1090\/memo\/1410","DOI":"10.1090\/memo\/1410"},{"issue":"34","key":"3202_CR21","doi-asserted-by":"publisher","first-page":"8505","DOI":"10.1073\/pnas.1718942115","volume":"115","author":"J Han","year":"2018","unstructured":"Han, J., Jentzen, A., Weinan, E.: Solving high-dimensional partial differential equations using deep learning. Proc. Natl. Acad. Sci. 115(34), 8505\u20138510 (2018)","journal-title":"Proc. Natl. Acad. Sci."},{"issue":"1","key":"3202_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41546-020-00047-w","volume":"5","author":"J Han","year":"2020","unstructured":"Han, J., Long, J.: Convergence of the deep BSDE method for coupled FBSDEs. Probab. Uncertain. Quant. Risk 5(1), 1\u201333 (2020)","journal-title":"Probab. Uncertain. Quant. Risk"},{"key":"3202_CR23","doi-asserted-by":"crossref","unstructured":"Henry-Labordere, P.: Deep primal-dual algorithm for BSDEs: Applications of machine learning to CVA and IM. Available at SSRN 3071506 (2017)","DOI":"10.2139\/ssrn.3071506"},{"key":"3202_CR24","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1016\/j.matcom.2024.08.002","volume":"227","author":"Z Huang","year":"2025","unstructured":"Huang, Z., Negyesi, B., Oosterlee, C.W.: Convergence of the deep BSDE method for stochastic control problems formulated through the stochastic maximum principle. Math. Comput. Simul. 227, 553\u2013568 (2025)","journal-title":"Math. Comput. Simul."},{"key":"3202_CR25","unstructured":"Huang, Z., Oosterlee, C.W.: Convergence of the Markovian iteration for coupled FBSDEs via a differentiation approach. arXiv preprint arXiv:2504.02814 (2025)"},{"issue":"324","key":"3202_CR26","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1090\/mcom\/3514","volume":"89","author":"C Hur\u00e9","year":"2020","unstructured":"Hur\u00e9, C., Pham, H., Warin, X.: Deep backward schemes for high-dimensional nonlinear PDEs. Math. Comput. 89(324), 1547\u20131579 (2020)","journal-title":"Math. Comput."},{"issue":"2","key":"3202_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42985-019-0006-9","volume":"1","author":"M Hutzenthaler","year":"2020","unstructured":"Hutzenthaler, M., Jentzen, A., Kruse, T., Nguyen, T.A.: A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations. SN Partial Differ. Equ. Appl 1(2), 1\u201334 (2020)","journal-title":"SN Partial Differ. Equ. Appl"},{"issue":"5","key":"3202_CR28","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.4310\/CMS.2021.v19.n5.a1","volume":"19","author":"A Jentzen","year":"2021","unstructured":"Jentzen, A., Salimova, D., Welti, T.: A proof that deep artificial neural networks overcome the curse of dimensionality in the numerical approximation of Kolmogorov partial differential equations with constant diffusion and nonlinear drift coefficients. Commun. Math. Sci. 19(5), 1167\u20131205 (2021)","journal-title":"Commun. Math. Sci."},{"issue":"3","key":"3202_CR29","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/MIS.2020.2971597","volume":"35","author":"S Ji","year":"2020","unstructured":"Ji, S., Peng, S., Peng, Y., Zhang, X.: Three algorithms for solving high-dimensional fully coupled FBSDEs through deep learning. IEEE Intell. Syst. 35(3), 71\u201384 (2020)","journal-title":"IEEE Intell. Syst."},{"issue":"4","key":"3202_CR30","doi-asserted-by":"publisher","first-page":"C873","DOI":"10.1137\/24M1647084","volume":"47","author":"S Ji","year":"2025","unstructured":"Ji, S., Peng, S., Peng, Y., Zhang, X.: A novel control method for solving high-dimensional Hamiltonian systems through deep neural networks. SIAM J. Sci. Comput. 47(4), C873\u2013C898 (2025)","journal-title":"SIAM J. Sci. Comput."},{"issue":"4","key":"3202_CR31","doi-asserted-by":"publisher","first-page":"391","DOI":"10.3934\/puqr.2021019","volume":"6","author":"Y Jiang","year":"2021","unstructured":"Jiang, Y., Li, J.: Convergence of the deep BSDE method for FBSDEs with non-Lipschitz coefficients. Probab. Uncertain. Quant. Risk 6(4), 391\u2013408 (2021)","journal-title":"Probab. Uncertain. Quant. Risk"},{"key":"3202_CR32","doi-asserted-by":"crossref","unstructured":"Kapllani, L., Teng, L.: A backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations. IMA J. Num. Anal. pp. draf022 (2025)","DOI":"10.1093\/imanum\/draf022"},{"issue":"6","key":"3202_CR33","doi-asserted-by":"publisher","first-page":"3595","DOI":"10.1093\/imanum\/drad092","volume":"44","author":"B Negyesi","year":"2024","unstructured":"Negyesi, B., Andersson, K., Oosterlee, C.W.: The One Step Malliavin scheme: new discretization of BSDEs implemented with deep learning regressions. IMA J. Numer. Anal. 44(6), 3595\u20133647 (2024)","journal-title":"IMA J. Numer. Anal."},{"key":"3202_CR34","unstructured":"Negyesi, B., Huang, Z., Oosterlee, C.W.: Generalized convergence of the deep BSDE method: a step towards fully-coupled FBSDEs and applications in stochastic control. arXiv preprint arXiv:2403.18552 (2024)"},{"key":"3202_CR35","doi-asserted-by":"crossref","unstructured":"Raissi, M.: Forward\u2013backward stochastic neural networks: deep learning of high-dimensional partial differential equations. In: Peter Carr Gedenkschrift: Research Advances in Mathematical Finance, pp. 637\u2013655. World Scientific (2024)","DOI":"10.1142\/9789811280306_0018"},{"issue":"4","key":"3202_CR36","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.1093\/imanum\/drad060","volume":"44","author":"C Reisinger","year":"2024","unstructured":"Reisinger, C., Stockinger, W., Zhang, Y.: A posteriori error estimates for fully coupled Mckean-Vlasov forward-backward SDEs. IMA J. Numer. Anal. 44(4), 2323\u20132369 (2024)","journal-title":"IMA J. Numer. Anal."},{"key":"3202_CR37","unstructured":"Wang, Y., Ni, Y.H.: Deep BSDE-ML Learning and Its Application to Model-Free Optimal Control. Preprint arXiv:2201.01318 (2022)"},{"key":"3202_CR38","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4939-7256-2","volume-title":"Backward stochastic differential equations","author":"J Zhang","year":"2017","unstructured":"Zhang, J.: Backward stochastic differential equations. Springer, Berlin\/Heidelberg, Germany (2017)"}],"container-title":["Journal of Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-026-03202-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10915-026-03202-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-026-03202-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T07:14:29Z","timestamp":1772608469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10915-026-03202-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["3202"],"URL":"https:\/\/doi.org\/10.1007\/s10915-026-03202-1","relation":{},"ISSN":["0885-7474","1573-7691"],"issn-type":[{"value":"0885-7474","type":"print"},{"value":"1573-7691","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]},"assertion":[{"value":"31 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The code that supports the findings is available from the corresponding author upon reasonable request.","order":6,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code availability"}}],"article-number":"77"}}