{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:15:37Z","timestamp":1771460137480,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62006238"],"award-info":[{"award-number":["62006238"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61922087"],"award-info":[{"award-number":["61922087"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the National Natural Science Foundationof Hunan Province","award":["2023JJ20052"],"award-info":[{"award-number":["2023JJ20052"]}]},{"name":"the Key National Natural Science Foundation of China under Grant","award":["62136005"],"award-info":[{"award-number":["62136005"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s10994-024-06696-8","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T17:10:08Z","timestamp":1737997808000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Gradient-based causal discovery with latent variables"],"prefix":"10.1007","volume":"114","author":[{"given":"Haotian","family":"Ni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian-Zuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiuqi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenping","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,27]]},"reference":[{"key":"6696_CR1","unstructured":"Bertsekas, D. (2016). Nonlinear Programming. Athena scientific optimization and computation series. Athena Scientific."},{"key":"6696_CR2","doi-asserted-by":"crossref","unstructured":"Bollen, K. A. (1989). Four. Structural equation models with observed variables, pp. 80\u2013150. John Wiley and Sons, Ltd.","DOI":"10.1002\/9781118619179.ch4"},{"issue":"6","key":"6696_CR3","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1214\/14-AOS1260","volume":"42","author":"P B\u00fchlmann","year":"2014","unstructured":"B\u00fchlmann, P., Peters, J., & Ernest, J. (2014). CAM: Causal additive models, high-dimensional order search and penalized regression. Annals of Statistics, 42(6), 2526\u20132556.","journal-title":"Annals of Statistics"},{"key":"6696_CR4","first-page":"507","volume":"3","author":"DM Chickering","year":"2003","unstructured":"Chickering, D. M. (2003). Optimal structure identification with greedy search. Journal of Machine Learning Research, 3, 507\u2013554.","journal-title":"Journal of Machine Learning Research"},{"key":"6696_CR5","first-page":"1287","volume":"5","author":"DM Chickering","year":"2004","unstructured":"Chickering, D. M., Heckerman, D., & Meek, C. (2004). Large-sample learning of bayesian networks is np-hard. Journal of Machine Learning Research, 5, 1287\u20131330.","journal-title":"Journal of Machine Learning Research"},{"key":"6696_CR6","unstructured":"Cussens, J. (2011). Bayesian network learning with cutting planes. In: Proceedings of the 27th conference on uncertainty in artificial intelligence, pp. 153\u2013160."},{"issue":"1\u20132","key":"6696_CR7","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s10107-016-1087-2","volume":"164","author":"J Cussens","year":"2017","unstructured":"Cussens, J., Haws, D., & Studen\u00fd, M. (2017). Polyhedral aspects of score equivalence in bayesian network structure learning. Mathematical Programming, 164(1\u20132), 285\u2013324.","journal-title":"Mathematical Programming"},{"issue":"1\u20132","key":"6696_CR8","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1007\/s10618-010-0178-6","volume":"22","author":"JA G\u00e1mez","year":"2011","unstructured":"G\u00e1mez, J. A., Mateo, J. L., & Puerta, J. M. (2011). Learning bayesian networks by hill climbing: efficient methods based on progressive restriction of the neighborhood. Data Mining and Knowledge Discovery, 22(1\u20132), 106\u2013148.","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"3","key":"6696_CR9","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/BF00994016","volume":"20","author":"D Heckerman","year":"1995","unstructured":"Heckerman, D., Geiger, D., & Chickering, D. M. (1995). Learning bayesian networks: The combination of knowledge and statistical data. Machine Learning, 20(3), 197\u2013243.","journal-title":"Machine Learning"},{"issue":"02","key":"6696_CR10","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1055\/s-0038-1634867","volume":"31","author":"DE Heckerman","year":"1992","unstructured":"Heckerman, D. E., Horvitz, E. J., & Nathwani, B. N. (1992). Toward normative expert systems: Part i the pathfinder project. Methods of Information in Medicine, 31(02), 90\u2013105.","journal-title":"Methods of Information in Medicine"},{"key":"6696_CR11","unstructured":"Hoyer, P. O., Janzing, D., Mooij, J. M., Peters, J., & Sch\u00f6lkopf, B. (2008). Nonlinear causal discovery with additive noise models. In: Advances in Neural Information Processing Systems, 21, pp. 689\u2013696."},{"key":"6696_CR12","unstructured":"Jaakkola, T., Sontag, D., Globerson, A., & Meila, M. (2010). Learning bayesian network structure using lp relaxations. In: Proceedings of the 13th international conference on artificial intelligence and statistics, pp. 358\u2013365."},{"key":"6696_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.artint.2012.01.002","volume":"182\u2013183","author":"D Janzing","year":"2012","unstructured":"Janzing, D., Mooij, J., Zhang, K., Lemeire, J., Zscheischler, J., Daniu\u0161is, P., Steudel, B., & Sch\u00f6lkopf, B. (2012). Information-geometric approach to inferring causal directions. Artificial Intelligence, 182\u2013183, 1\u201331.","journal-title":"Artificial Intelligence"},{"key":"6696_CR14","unstructured":"Kaltenpoth, D., & Vreeken, J. (2023). Causal discovery with hidden confounders using the algorithmic Markov condition. In: Evans, R.J., Shpitser, I. (eds.) Proceedings of the thirty-ninth conference on uncertainty in artificial intelligence. Proceedings of Machine Learning Research, vol. 216, pp. 1016\u20131026. PMLR."},{"key":"6696_CR15","unstructured":"Kingma, D. P., & Welling, M. (2014). Auto-encoding variational bayes. In: 2nd International conference on learning representations."},{"key":"6696_CR16","unstructured":"Kipf, T.N., & Welling, M. (2019). Variational graph auto-encoders. arXiv preprint arXiv:1611.07308."},{"key":"6696_CR17","unstructured":"Kusner, M. J., Loftus, J., Russell, C., & Silva, R. (2017). Counterfactual fairness. In: Advances in Neural Information Processing Systems, pp. 4066\u20134076."},{"key":"6696_CR18","unstructured":"Lachapelle, S., Brouillard, P., Deleu, T., & Lacoste-Julien, S. (2020). Gradient-based neural DAG learning. In: 8th International conference on learning representations."},{"issue":"6A","key":"6696_CR19","doi-asserted-by":"publisher","first-page":"3151","DOI":"10.1214\/17-AOS1654","volume":"46","author":"P Nandy","year":"2018","unstructured":"Nandy, P., Hauser, A., & Maathuis, M. H. (2018). High-dimensional consistency in score-based and hybrid structure learning. The Annals of Statistics, 46(6A), 3151\u20133183.","journal-title":"The Annals of Statistics"},{"key":"6696_CR20","doi-asserted-by":"crossref","unstructured":"Opgen-Rhein, Strimmer, K. (2007). From correlation to causation networks: a simple approximate learning algorithm and its application to high-dimensional plant gene expression data. BMC Systems Biology, 1(1), 37.","DOI":"10.1186\/1752-0509-1-37"},{"key":"6696_CR21","volume-title":"Causality: models, reasoning and inference","author":"J Pearl","year":"2000","unstructured":"Pearl, J. (2000). Causality: models, reasoning and inference. Cambridge: Cambridge University Press."},{"issue":"1","key":"6696_CR22","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1093\/biomet\/ast043","volume":"101","author":"J Peters","year":"2014","unstructured":"Peters, J., & B\u00fchlmann, P. (2014). Identifiability of gaussian structural equation models with equal error variances. Biometrika, 101(1), 219\u2013228.","journal-title":"Biometrika"},{"key":"6696_CR23","volume-title":"Elements of causal inference: Foundations and learning algorithms","author":"J Peters","year":"2017","unstructured":"Peters, J., Janzing, D., & Sch\u00f6lkopf, B. (2017). Elements of causal inference: Foundations and learning algorithms. Cambridge: The MIT Press."},{"issue":"5721","key":"6696_CR24","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1126\/science.1105809","volume":"308","author":"K Sachs","year":"2005","unstructured":"Sachs, K., Perez, O., Pe\u2019er, D., Lauffenburger, D. A., & Nolan, G. P. (2005). Causal protein-signaling networks derived from multiparameter single-cell data. Science, 308(5721), 523\u2013529.","journal-title":"Science"},{"issue":"4","key":"6696_CR25","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1057\/jors.2011.7","volume":"63","author":"A Sanford","year":"2012","unstructured":"Sanford, A., & Moosa, I. (2012). A bayesian network structure for operational risk modelling in structured finance operations. Journal of the Operational Research Society, 63(4), 431\u2013444.","journal-title":"Journal of the Operational Research Society"},{"key":"6696_CR26","first-page":"2003","volume":"7","author":"S Shimizu","year":"2006","unstructured":"Shimizu, S., Hoyer, P. O., Hyv\u00e4rinen, A., & Kerminen, A. (2006). A linear non-gaussian acyclic model for causal discovery. Journal of Machine Learning Research, 7, 2003\u20132030.","journal-title":"Journal of Machine Learning Research"},{"key":"6696_CR27","first-page":"2003","volume":"7","author":"S Shimizu","year":"2006","unstructured":"Shimizu, S., Hoyer, P. O., Hyv\u00e4rinen, A., & Kerminen, A. J. (2006). A linear non-gaussian acyclic model for causal discovery. Journal of Machine Learning Research, 7, 2003\u20132030.","journal-title":"Journal of Machine Learning Research"},{"key":"6696_CR28","first-page":"1225","volume":"12","author":"S Shimizu","year":"2011","unstructured":"Shimizu, S., Inazumi, T., Sogawa, Y., Hyv\u00e4rinen, A., Kawahara, Y., Washio, T., Hoyer, P. O., & Bollen, K. (2011). Directlingam: A direct method for learning a linear non-gaussian structural equation model. Journal of Machine Learning Research, 12, 1225\u20131248.","journal-title":"Journal of Machine Learning Research"},{"key":"6696_CR29","unstructured":"Silander, T., & Myllym\u00e4ki, P. (2006). A simple approach for finding the globally optimal bayesian network structure. In: Proceedings of the 22nd conference in uncertainty in artificial intelligence."},{"key":"6696_CR30","unstructured":"Singh, A. P., & Moore, A. W. (2005). Finding optimal bayesian networks by dynamic programming. Citeseer."},{"key":"6696_CR31","unstructured":"Spirtes, P., Meek, C., & Richardson, T. (1995). Causal inference in the presence of latent variables and selection bias. In: Proceedings of the 11th conference on uncertainty in artificial intelligence, pp. 499\u2013506."},{"key":"6696_CR32","volume-title":"Causation, prediction, and search","author":"P Spirtes","year":"2000","unstructured":"Spirtes, P., Glymour, C., & Scheines, R. (2000). Causation, prediction, and search. Cambridge: The MIT Press."},{"issue":"1","key":"6696_CR33","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10994-006-6889-7","volume":"65","author":"I Tsamardinos","year":"2006","unstructured":"Tsamardinos, I., Brown, L. E., & Aliferis, C. F. (2006). The max-min hill-climbing bayesian network structure learning algorithm. Machine Learning, 65(1), 31\u201378.","journal-title":"Machine Learning"},{"key":"6696_CR34","unstructured":"Yu, Y., Chen, J., Gao, T., & Yu, M. (2019). DAG-GNN: DAG structure learning with graph neural networks. In: Chaudhuri, K., & Salakhutdinov, R. (eds.) Proceedings of the 36th international conference on machine learning, pp. 7154\u20137163."},{"key":"6696_CR35","unstructured":"Zhang, K., & Hyv\u00e4rinen, A. (2009). On the identifiability of the post-nonlinear causal model. In: Proceedings of the 25th conference on uncertainty in artificial intelligence, pp. 647\u2013655."},{"key":"6696_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, K., Wang, Z., Zhang, J., & Sch\u00f6lkopf, B. (2015). On estimation of functional causal models: General results and application to the post-nonlinear causal model. ACM Transactions on Intelligent Systems and Technology, 7(2).","DOI":"10.1145\/2700476"},{"key":"6696_CR37","unstructured":"Zheng, X., Aragam, B., Ravikumar, P., & Xing, E.P. (2018). Dags with NO TEARS: Continuous optimization for structure learning. In: Advances in Neural Information Processing Systems, 31, pp. 9492\u20139503."},{"key":"6696_CR38","unstructured":"Zheng, X., Dan, C., Aragam, B., Ravikumar, P., & Xing, E. (2020). Learning sparse nonparametric dags. In: International conference on artificial intelligence and statistics, pp. 3414\u20133425."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06696-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-024-06696-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06696-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T01:03:26Z","timestamp":1769475806000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-024-06696-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,27]]},"references-count":38,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["6696"],"URL":"https:\/\/doi.org\/10.1007\/s10994-024-06696-8","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,27]]},"assertion":[{"value":"29 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"46"}}