{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T10:15:58Z","timestamp":1783678558075,"version":"3.55.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12471372"],"award-info":[{"award-number":["12471372"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sci Comput"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s10915-026-03379-5","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T13:43:09Z","timestamp":1782394989000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Optimal-order Backpropagation Algorithm for Stochastic Neural Networks"],"prefix":"10.1007","volume":"108","author":[{"given":"Daili","family":"Sheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0570-0124","authenticated-orcid":false,"given":"Minghui","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanqi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"3379_CR1","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","volume":"76","author":"M Abdar","year":"2021","unstructured":"Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U.R.: A review of uncertainty quantification in deep learning: techniques, applications and challenges. Inf. Fusion 76, 243\u2013297 (2021). https:\/\/doi.org\/10.1016\/j.inffus.2021.05.008","journal-title":"Inf. Fusion"},{"key":"3379_CR2","doi-asserted-by":"crossref","unstructured":"Gustafsson, F.K., Danelljan, M., Schon, T.B.: Evaluating scalable bayesian deep learning methods for robust computer vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 318\u2013319. (2020)","DOI":"10.1109\/CVPRW50498.2020.00167"},{"key":"3379_CR3","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in bayesian deep learning for computer vision? Adv. Neural. Inf. Process. Syst. , 30 (2017)"},{"issue":"4","key":"3379_CR4","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10444-025-10241-z","volume":"51","author":"Y Dai","year":"2025","unstructured":"Dai, Y., Jin, B., Sau, R.C., Zhou, Z.: Solving elliptic optimal control problems via neural networks and optimality system. Adv. Comput. Math. 51(4), 31 (2025). https:\/\/doi.org\/10.1007\/s10444-025-10241-z","journal-title":"Adv. Comput. Math."},{"issue":"2","key":"3379_CR5","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1137\/24M1642627","volume":"47","author":"J Ning","year":"2025","unstructured":"Ning, J., Han, F., Zou, J.: A direct sampling method and its integration with deep learning for inverse scattering problems with phaseless data. SIAM J. Sci. Comput. 47(2), 343\u2013368 (2025). https:\/\/doi.org\/10.1137\/24M1642627","journal-title":"SIAM J. Sci. Comput."},{"issue":"1","key":"3379_CR6","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ad0dba","volume":"40","author":"J Ning","year":"2023","unstructured":"Ning, J., Han, F., Zou, J.: A direct sampling-based deep learning approach for inverse medium scattering problems. Inverse Probl. 40(1), 015005 (2023). https:\/\/doi.org\/10.1088\/1361-6420\/ad0dba","journal-title":"Inverse Probl."},{"key":"3379_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110771","volume":"448","author":"Y Gao","year":"2022","unstructured":"Gao, Y., Liu, H., Wang, X., Zhang, K.: On an artificial neural network for inverse scattering problems. J. Comput. Phys. 448, 110771 (2022). https:\/\/doi.org\/10.1016\/j.jcp.2021.110771","journal-title":"J. Comput. Phys."},{"key":"3379_CR8","first-page":"6571","volume":"31","author":"RT Chen","year":"2018","unstructured":"Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.K.: Neural ordinary differential equations. Adv. Neural. Inf. Process. Syst. 31, 6571\u20136583 (2018)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3379_CR9","unstructured":"Li, X., Wong, T.-K.L., Chen, R.T.Q., Duvenaud, D.K.: Scalable gradients and variational inference for stochastic differential equations. In: Proceedings of The 2nd Symposium on Advances in Approximate Bayesian Inference. Proceedings of Machine Learning Research, vol. 118, pp. 1\u201328. (2020)"},{"key":"3379_CR10","unstructured":"Hegde, P., Heinonen, M., L\u00e4hdesm\u00e4ki, H., Kaski, S.: Deep learning with differential gaussian process flows. In: Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 89, pp. 1812\u20131821. (2019)"},{"key":"3379_CR11","unstructured":"Innes, M., Edelman, A., Fischer, K., Rackauckas, C., Saba, E., Shah, V.B., Tebbutt, W.: A differentiable programming system to bridge machine learning and scientific computing, (2019). arXiv preprint arXiv:1907.07587"},{"key":"3379_CR12","doi-asserted-by":"publisher","unstructured":"Liu, X., Xiao, T., Si, S., Cao, Q., Kumar, S., Hsieh, C.-J.: How does noise help robustness? explanation and exploration under the neural sde framework. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 282\u2013290 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00036","DOI":"10.1109\/CVPR42600.2020.00036"},{"key":"3379_CR13","unstructured":"Tzen, B., Raginsky, M.: Neural stochastic differential equations: Deep latent gaussian models in the diffusion limit, (2019). arXiv preprint arXiv:1905.09883"},{"key":"3379_CR14","unstructured":"Dupont, E., Doucet, A., Teh, Y.W.: Augmented neural odes. Adv. Neural. Inf. Process. Syst. 32, (2019)"},{"issue":"1","key":"3379_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40304-017-0103-z","volume":"5","author":"E Weinan","year":"2017","unstructured":"Weinan, E.: A proposal on machine learning via dynamical systems. Commun. Math. Stat. 5(1), 1\u201311 (2017). https:\/\/doi.org\/10.1007\/s40304-017-0103-z","journal-title":"Commun. Math. Stat."},{"issue":"1","key":"3379_CR16","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9a90","volume":"34","author":"E Haber","year":"2017","unstructured":"Haber, E., Ruthotto, L.: Stable architectures for deep neural networks. Inverse Probl. 34(1), 014004 (2017). https:\/\/doi.org\/10.1088\/1361-6420\/aa9a90","journal-title":"Inverse Probl."},{"issue":"165","key":"3379_CR17","first-page":"1","volume":"18","author":"Q Li","year":"2018","unstructured":"Li, Q., Chen, L., Tai, C.: Maximum principle based algorithms for deep learning. J. Mach. Learn. Res. 18(165), 1\u201329 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"3379_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/sym15091724","author":"L Di Persio","year":"2023","unstructured":"Di Persio, L., Garbelli, M.: From optimal control to mean field optimal transport via stochastic neural networks. Symmetry (2023). https:\/\/doi.org\/10.3390\/sym15091724","journal-title":"Symmetry"},{"issue":"1","key":"3379_CR19","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1137\/20M1316640","volume":"59","author":"C Hur\u00e9","year":"2021","unstructured":"Hur\u00e9, C., Pham, H., Bachouch, A., Langren\u00e9, N.: Deep neural networks algorithms for stochastic control problems on finite horizon: convergence analysis. SIAM J. Numer. Anal. 59(1), 525\u2013557 (2021). https:\/\/doi.org\/10.1137\/20M1316640","journal-title":"SIAM J. Numer. Anal."},{"key":"3379_CR20","unstructured":"Jia, J., Benson, A.R.: Neural jump stochastic differential equations. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"3379_CR21","first-page":"18747","volume":"34","author":"P Kidger","year":"2021","unstructured":"Kidger, P., Foster, J., Li, X.C., Lyons, T.: Efficient and accurate gradients for neural sdes. Adv. Neural. Inf. Process. Syst. 34, 18747\u201318761 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"3379_CR22","unstructured":"Kong, L., Sun, J., Zhang, C.: Sde-net: Equipping deep neural networks with uncertainty estimates, (2020). arXiv preprint arXiv:2008.10546"},{"key":"3379_CR23","doi-asserted-by":"publisher","DOI":"10.4208\/eajam.190420.200420","author":"R Archibald","year":"2020","unstructured":"Archibald, R., Feng, B., Jiongmin, Y.: A stochastic gradient descent approach for stochastic optimal control. East Asian J. Appl. Math. (2020). https:\/\/doi.org\/10.4208\/eajam.190420.200420","journal-title":"East Asian J. Appl. Math."},{"issue":"10","key":"3379_CR24","doi-asserted-by":"publisher","first-page":"2807","DOI":"10.3934\/dcdss.2022062","volume":"15","author":"R Archibald","year":"2022","unstructured":"Archibald, R., Bao, F., Cao, Y., Zhang, H.: A backward SDE method for uncertainty quantification in deep learning. Discrete Contin. Dyn. Syst. Ser. S 15(10), 2807\u20132835 (2022). https:\/\/doi.org\/10.3934\/dcdss.2022062","journal-title":"Discrete Contin. Dyn. Syst. Ser. S"},{"issue":"2","key":"3379_CR25","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1137\/22M1523765","volume":"62","author":"R Archibald","year":"2024","unstructured":"Archibald, R., Bao, F., Cao, Y., Sun, H.: Numerical analysis for convergence of a sample-wise backpropagation method for training stochastic neural networks. SIAM J. Numer. Anal. 62(2), 593\u2013621 (2024). https:\/\/doi.org\/10.1137\/22M1523765","journal-title":"SIAM J. Numer. Anal."},{"issue":"4","key":"3379_CR26","doi-asserted-by":"publisher","first-page":"966","DOI":"10.1137\/0328054","volume":"28","author":"S Peng","year":"1990","unstructured":"Peng, S.: A general stochastic maximum principle for optimal control problems. SIAM J. Control. Optim. 28(4), 966\u2013979 (1990). https:\/\/doi.org\/10.1137\/0328054","journal-title":"SIAM J. Control. Optim."},{"key":"3379_CR27","doi-asserted-by":"publisher","unstructured":"Touzi, N.: Optimal Stochastic Control, Stochastic Target Problems, and Backward SDE vol. 29. Springer. New York (2012). https:\/\/doi.org\/10.1007\/978-1-4614-4286-8","DOI":"10.1007\/978-1-4614-4286-8"},{"key":"3379_CR28","doi-asserted-by":"publisher","first-page":"1468","DOI":"10.1214\/EJP.v10-295","volume":"10","author":"J Cvitanic","year":"2005","unstructured":"Cvitanic, J., Zhang, J.: The steepest descent method for forward-backward sdes. Electron. J. Probab. 10, 1468\u20131495 (2005). https:\/\/doi.org\/10.1214\/EJP.v10-295","journal-title":"Electron. J. Probab."},{"issue":"1","key":"3379_CR29","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1214\/105051605000000674","volume":"16","author":"F Delarue","year":"2006","unstructured":"Delarue, F., Menozzi, S.: A forward-backward stochastic algorithm for quasi-linear pdes. Ann. Appl. Probab. 16(1), 140\u2013184 (2006). https:\/\/doi.org\/10.1214\/105051605000000674","journal-title":"Ann. Appl. Probab."},{"issue":"3","key":"3379_CR30","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1214\/aoap\/1034968235","volume":"6","author":"J Douglas Jr","year":"1996","unstructured":"Douglas, J., Jr., Ma, J., Protter, P.: Numerical methods for forward-backward stochastic differential equations. Ann. Appl. Probab. 6(3), 940\u2013968 (1996). https:\/\/doi.org\/10.1214\/aoap\/1034968235","journal-title":"Ann. Appl. Probab."},{"issue":"5","key":"3379_CR31","doi-asserted-by":"publisher","first-page":"2636","DOI":"10.1137\/06067393X","volume":"46","author":"J Ma","year":"2008","unstructured":"Ma, J., Shen, J., Zhao, Y.: On numerical approximations of forward-backward stochastic differential equations. SIAM J. Numer. Anal. 46(5), 2636\u20132661 (2008). https:\/\/doi.org\/10.1137\/06067393X","journal-title":"SIAM J. Numer. Anal."},{"issue":"4","key":"3379_CR32","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1137\/130941274","volume":"36","author":"W Zhao","year":"2014","unstructured":"Zhao, W., Fu, Y., Zhou, T.: New kinds of high-order multistep schemes for coupled forward backward stochastic differential equations. SIAM J. Sci. Comput. 36(4), 1731\u20131751 (2014). https:\/\/doi.org\/10.1137\/130941274","journal-title":"SIAM J. Sci. Comput."},{"key":"3379_CR33","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1007\/s11425-013-4764-0","volume":"57","author":"W Zhao","year":"2014","unstructured":"Zhao, W., Li, Y., Fu, Y.: Second-order schemes for solving decoupled forward backward stochastic differential equations. Sci China Math 57, 665\u2013686 (2014). https:\/\/doi.org\/10.1007\/s11425-013-4764-0","journal-title":"Sci China Math"},{"issue":"3","key":"3379_CR34","doi-asserted-by":"publisher","first-page":"618","DOI":"10.4208\/cicp.280113.190813a","volume":"15","author":"W Zhao","year":"2014","unstructured":"Zhao, W., Zhang, W., Ju, L.: A numerical method and its error estimates for the decoupled forward-backward stochastic differential equations. Commun. Comput. Phys. 15(3), 618\u2013646 (2014). https:\/\/doi.org\/10.4208\/cicp.280113.190813a","journal-title":"Commun. Comput. Phys."},{"issue":"2","key":"3379_CR35","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10915-020-01358-y","volume":"85","author":"R Archibald","year":"2020","unstructured":"Archibald, R., Bao, F., Yong, J., Zhou, T.: An efficient numerical algorithm for solving data driven feedback control problems. J. Sci. Comput. 85(2), 51 (2020). https:\/\/doi.org\/10.1007\/s10915-020-01358-y","journal-title":"J. Sci. Comput."},{"key":"3379_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112238","volume":"488","author":"R Archibald","year":"2023","unstructured":"Archibald, R., Bao, F., Yong, J.: A stochastic maximum principle approach for reinforcement learning with parameterized environment. J. Comput. Phys. 488, 112238 (2023). https:\/\/doi.org\/10.1016\/j.jcp.2023.112238","journal-title":"J. Comput. Phys."},{"key":"3379_CR37","doi-asserted-by":"publisher","unstructured":"Yong, J., Zhou, X.: Stochastic Controls: Hamiltonian Systems and HJB Equations vol. 43. Springer, New York (2012). https:\/\/doi.org\/10.1007\/978-1-4612-1466-3","DOI":"10.1007\/978-1-4612-1466-3"},{"key":"3379_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, J.: Backward stochastic differential equations. In: Backward Stochastic Differential Equations: From Linear to Fully Nonlinear Theory, pp. 79\u201399. Springer, New York (2017). https:\/\/doi.org\/10.1007\/978-1-4939-7256-2","DOI":"10.1007\/978-1-4939-7256-2"},{"issue":"6","key":"3379_CR39","doi-asserted-by":"publisher","first-page":"2982","DOI":"10.1137\/17M1123559","volume":"55","author":"B Gong","year":"2017","unstructured":"Gong, B., Liu, W., Tang, T., Zhao, W., Zhou, T.: An efficient gradient projection method for stochastic optimal control problems. SIAM J. Numer. Anal. 55(6), 2982\u20133005 (2017). https:\/\/doi.org\/10.1137\/17M1123559","journal-title":"SIAM J. Numer. Anal."},{"issue":"1\u20132","key":"3379_CR40","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1080\/17442509108833727","volume":"37","author":"S Peng","year":"1991","unstructured":"Peng, S.: Probabilistic interpretation for systems of quasilinear parabolic partial differential equations. Stoch. Stoch. Rep. 37(1\u20132), 61\u201374 (1991). https:\/\/doi.org\/10.1080\/17442509108833727","journal-title":"Stoch. Stoch. Rep."},{"key":"3379_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3934\/naco.2026009","volume":"19","author":"H Sun","year":"2026","unstructured":"Sun, H., Bao, F.: Batch sample-wise stochastic optimal control via stochastic maximum principle. Numer. Algebra Control Optim. 19, 1\u201334 (2026). https:\/\/doi.org\/10.3934\/naco.2026009","journal-title":"Numer. Algebra Control Optim."}],"container-title":["Journal of Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-026-03379-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10915-026-03379-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10915-026-03379-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T09:38:37Z","timestamp":1783676317000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10915-026-03379-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["3379"],"URL":"https:\/\/doi.org\/10.1007\/s10915-026-03379-5","relation":{},"ISSN":["0885-7474","1573-7691"],"issn-type":[{"value":"0885-7474","type":"print"},{"value":"1573-7691","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"4 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 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 they have no conflicting financial interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}],"article-number":"56"}}