{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T00:24:29Z","timestamp":1755217469593,"version":"3.43.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T00:00:00Z","timestamp":1753315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["EXC 2181\/1 - 390900948"],"award-info":[{"award-number":["EXC 2181\/1 - 390900948"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100019180","name":"HORIZON EUROPE European Research Council","doi-asserted-by":"publisher","award":["101071786"],"award-info":[{"award-number":["101071786"]}],"id":[{"id":"10.13039\/100019180","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001661","name":"Ruprecht-Karls-Universit\u00e4t Heidelberg","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001661","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>We provide an implementation to compute the flat metric in any dimension. The flat metric, also called dual bounded Lipschitz distance, generalizes the well-known Wasserstein distance <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$$W_1$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:msub>\n                    <mml:mi>W<\/mml:mi>\n                    <mml:mn>1<\/mml:mn>\n                  <\/mml:msub>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula> to the case that the distributions are of unequal total mass. Thus, our implementation adapts very well to mass differences and uses them to distinguish between different distributions. This is of particular interest for unbalanced optimal transport tasks and for the analysis of data distributions where the sample size is important or normalization is not possible. The core of the method is based on a neural network to determine an optimal test function realizing the distance between two given measures. Special focus was put on achieving comparability of pairwise computed distances from independently trained networks. We tested the quality of the output in several experiments where ground truth was available as well as with simulated data.<\/jats:p>","DOI":"10.1007\/s10994-025-06828-8","type":"journal-article","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T20:54:28Z","timestamp":1753390468000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Computing the distance between unbalanced distributions: the flat metric"],"prefix":"10.1007","volume":"114","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-2666-2670","authenticated-orcid":false,"given":"Henri","family":"Schmidt","sequence":"first","affiliation":[]},{"given":"Christian","family":"D\u00fcll","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,24]]},"reference":[{"key":"6828_CR1","unstructured":"Anil, C., Lucas, J., & Grosse, R. (2019). Sorting out Lipschitz function approximation. In: K. Chaudhuri, & R. Salakhutdinov (Eds.), Proceedings of the 36th international conference on machine learning, proceedings of machine learning research, (vol\u00a097, pp. 291\u2013301). PMLR. https:\/\/proceedings.mlr.press\/v97\/anil19a.html"},{"key":"6828_CR2","unstructured":"Balaji, Y., Chellappa, R., & Feizi, S. (2020). Robust optimal transport with applications in generative modeling and domain adaptation. In: Proceedings of the 34th International conference on neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, NIPS\u201920"},{"issue":"2","key":"6828_CR3","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1137\/0708036","volume":"8","author":"A Bj\u00f6rck","year":"1971","unstructured":"Bj\u00f6rck, A., & Bowie, C. (1971). An iterative algorithm for computing the best estimate of an orthogonal matrix. SIAM Journal on Numerical Analysis, 8(2), 358\u2013364. https:\/\/doi.org\/10.1137\/0708036","journal-title":"SIAM Journal on Numerical Analysis"},{"key":"6828_CR4","unstructured":"Chernodub, A., & Nowicki, D. (2017). Norm-preserving orthogonal permutation linear unit activation functions (oplu). arXiv:1604.02313"},{"issue":"314","key":"6828_CR5","doi-asserted-by":"publisher","first-page":"2563","DOI":"10.1090\/mcom\/3303","volume":"87","author":"L Chizat","year":"2018","unstructured":"Chizat, L., Peyr\u00e9, G., Schmitzer, B., & Vialard, F. (2018). Scaling algorithms for unbalanced optimal transport problems. Mathematics of Computation, 87(314), 2563\u20132609. https:\/\/doi.org\/10.1090\/mcom\/3303","journal-title":"Mathematics of Computation"},{"key":"6828_CR6","unstructured":"Cuturi, M. (2013). Sinkhorn distances: Lightspeed computation of optimal transport. In: C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in Neural information processing systems (Vol. 26). Curran Associates Inc."},{"key":"6828_CR7","doi-asserted-by":"crossref","unstructured":"D\u00fcll, C., Gwiazda, P., Marciniak-Czochra, A., & Skrzeczkowski, J. (2022). Spaces of measures and their applications to structured population models, Cambridge monographs on applied and computational mathematics (Vol. 36). Cambridge University Press.","DOI":"10.1017\/9781009004770"},{"key":"6828_CR8","unstructured":"D\u00fcll, C. (2024). Generalising nonlinear population models- Radon measures, Polish spaces and the flat norm. PhD thesis, Heidelberg University- Faculty of Mathematics and Computer Science, https:\/\/archiv.ub.uni-heidelberg.de\/volltextserver\/35450\/1\/thesis_christian_duell.pdf"},{"key":"6828_CR9","unstructured":"Fatras, K., Sejourne, T., Flamary, R., & Courty, N. (2021). Unbalanced minibatch optimal transport; applications to domain adaptation. In: M. Meila, & T. Zhang (Eds.), Proceedings of the 38th international conference on machine learning, proceedings of machine learning research (vol. 139, pp. 3186\u20133197) PMLR. https:\/\/proceedings.mlr.press\/v139\/fatras21a.html"},{"key":"6828_CR10","unstructured":"Folland, G. B. (1984). Real analysis. In: Pure and applied mathematics (New York). John Wiley & Sons, Inc."},{"key":"6828_CR11","doi-asserted-by":"publisher","unstructured":"Geiger, C., & Kanzow, C. (2002). Theorie und numerik restringierter optimierungsaufgaben. Springer. https:\/\/doi.org\/10.1007\/978-3-642-56004-0","DOI":"10.1007\/978-3-642-56004-0"},{"key":"6828_CR12","doi-asserted-by":"publisher","unstructured":"Grauman, K., & Darrell, T. (2004). Fast contour matching using approximate earth mover\u2019s distance. In Proceedings of the 2004 IEEE computer society conference on computer vision and pattern recognition. CVPR. https:\/\/doi.org\/10.1109\/CVPR.2004.1315035","DOI":"10.1109\/CVPR.2004.1315035"},{"key":"6828_CR13","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. C. (2017). Improved training of Wasserstein GANs. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 30). Curran Associates Inc."},{"issue":"1","key":"6828_CR14","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s11117-017-0503-z","volume":"22","author":"P Gwiazda","year":"2018","unstructured":"Gwiazda, P., Marciniak-Czochra, A., & Thieme, H. R. (2018). Measures under the flat norm as ordered normed vector space. Positivity, 22(1), 105\u2013138. https:\/\/doi.org\/10.1007\/s11117-017-0503-z","journal-title":"Positivity"},{"key":"6828_CR15","unstructured":"Kingma, D. P. & Ba, J. (2015). Adam: A method for stochastic optimization. In: Y. Bengio, Y. LeCun (Eds.), 3rd international conference on learning representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, conference track proceedings. arXiv:1412.6980"},{"issue":"3","key":"6828_CR16","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/s10915-024-02586-2","volume":"100","author":"R Lakshmanan","year":"2024","unstructured":"Lakshmanan, R., & Pichler, A. (2024). Unbalanced optimal transport and maximum mean discrepancies: Interconnections and rapid evaluation. Journal of Scientific Computing, 100(3), 72. https:\/\/doi.org\/10.1007\/s10915-024-02586-2","journal-title":"Journal of Scientific Computing"},{"key":"6828_CR17","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.1109\/TCI.2020.3012954","volume":"6","author":"J Lee","year":"2020","unstructured":"Lee, J., Bertrand, N. P., & Rozell, C. J. (2020). Unbalanced optimal transport regularization for imaging problems. IEEE Transactions on Computational Imaging, 6, 1219\u20131232. https:\/\/doi.org\/10.1109\/TCI.2020.3012954","journal-title":"IEEE Transactions on Computational Imaging"},{"issue":"4","key":"6828_CR18","doi-asserted-by":"publisher","first-page":"2833","DOI":"10.1137\/140975528","volume":"7","author":"J Lellmann","year":"2014","unstructured":"Lellmann, J., Lorenz, D. A., Sch\u00f6nlieb, C., & Valkonen, T. (2014). Imaging with Kantorovich-Rubinstein discrepancy. SIAM Journal on Imaging Sciences, 7(4), 2833\u20132859. https:\/\/doi.org\/10.1137\/140975528","journal-title":"SIAM Journal on Imaging Sciences"},{"key":"6828_CR19","doi-asserted-by":"publisher","DOI":"10.1093\/gji\/ggac119","author":"D Li","year":"2022","unstructured":"Li, D., Lamoureux, M., & Liao, W. (2022). Application of an unbalanced optimal transport distance and a mixed l1\/wasserstein distance to full waveform inversion. Geophysical Journal International. https:\/\/doi.org\/10.1093\/gji\/ggac119","journal-title":"Geophysical Journal International"},{"issue":"5","key":"6828_CR20","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1109\/TPAMI.2007.1058","volume":"29","author":"H Ling","year":"2007","unstructured":"Ling, H., & Okada, K. (2007). An efficient earth mover\u2019s distance algorithm for robust histogram comparison. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(5), 840\u2013853. https:\/\/doi.org\/10.1109\/TPAMI.2007.1058","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6828_CR21","unstructured":"Mukherjee, D., Guha, A., Solomon, J. M., Sun, Y., & Yurochkin, M. (2021). Outlier-robust optimal transport. In: M. Meila, & T. Zhang (Eds.), Proceedings of the 38th international conference on machine learning, proceedings of machine learning research (vol. 139, pp. 7850\u20137860). PMLR. https:\/\/proceedings.mlr.press\/v139\/mukherjee21a.html"},{"issue":"5\u20136","key":"6828_CR22","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1561\/2200000073","volume":"11","author":"G Peyr\u00e9","year":"2019","unstructured":"Peyr\u00e9, G., & Cuturi, M. (2019). Computational optimal transport: With applications to data science. Foundations and Trends in Machine Learning, 11(5\u20136), 355\u2013607. https:\/\/doi.org\/10.1561\/2200000073","journal-title":"Foundations and Trends in Machine Learning"},{"key":"6828_CR23","doi-asserted-by":"publisher","unstructured":"Peyr\u00e9, G., Fadili, J., & Rabin, J. (2012). Wasserstein active contours. In: 2012 19th IEEE international conference on image processing (pp. 2541\u20132544). https:\/\/doi.org\/10.1109\/ICIP.2012.6467416","DOI":"10.1109\/ICIP.2012.6467416"},{"issue":"1","key":"6828_CR24","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s00205-013-0669-x","volume":"211","author":"B Piccoli","year":"2014","unstructured":"Piccoli, B., & Rossi, F. (2014). Generalized Wasserstein distance and its application to transport equations with source. Archive for Rational Mechanics and Analysis, 211(1), 335\u2013358. https:\/\/doi.org\/10.1007\/s00205-013-0669-x","journal-title":"Archive for Rational Mechanics and Analysis"},{"issue":"4","key":"6828_CR25","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1016\/j.cell.2019.01.006","volume":"176","author":"G Schiebinger","year":"2019","unstructured":"Schiebinger, G., Shu, J., Tabaka, M., Cleary, B., Subramanian, V., Solomon, A., Gould, J., Liu, S., Lin, S., Berube, P., Lee, L., Chen, J., Brumbaugh, J., Rigollet, P., Hochedlinger, K., Jaenisch, R., Regev, A., & Lander, E. S. (2019). Optimal-transport analysis of single-cell gene expression identifies developmental trajectories in reprogramming. Cell, 176(4), 928-943.e22. https:\/\/doi.org\/10.1016\/j.cell.2019.01.006","journal-title":"Cell"},{"key":"6828_CR26","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1109\/ACCESS.2016.2639065","volume":"5","author":"J Schrieber","year":"2017","unstructured":"Schrieber, J., Schuhmacher, D., & Gottschlich, C. (2017). Dotmark \u2013 a benchmark for discrete optimal transport. IEEE Access, 5, 271\u2013282. https:\/\/doi.org\/10.1109\/ACCESS.2016.2639065","journal-title":"IEEE Access"},{"key":"6828_CR27","unstructured":"Sonthalia, R., & Gilbert, A. C. (2020). Dual regularized optimal transport. arXiv:2012.03126"},{"key":"6828_CR28","doi-asserted-by":"publisher","first-page":"10006","DOI":"10.1609\/aaai.v37i8.26193","volume":"37","author":"H Tran","year":"2023","unstructured":"Tran, H., Janati, H., Courty, N., Flamary, R., Redko, I., Demetci, P., & Singh, R. (2023). Unbalanced co-optimal transport. Proceedings of the AAAI Conference on Artificial Intelligence, 37, 10006\u201310016. https:\/\/doi.org\/10.1609\/aaai.v37i8.26193","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"6828_CR29","unstructured":"Tsuzuku, Y., Sato, I., & Sugiyama, M. (2018). Lipschitz-margin training: Scalable certification of perturbation invariance for deep neural networks. In: S. Bengio, H. Wallach, & H. Larochelle (Eds.), Advances in neural information processing systems (Vol. 31). Curran Associates, Inc."},{"key":"6828_CR30","unstructured":"Ulikowska, A. (2013). Structured population models in metric spaces. PhD thesis, University of Warsaw - Faculty of Mathematics, Informatics and Mechanics. https:\/\/depotuw.ceon.pl\/handle\/item\/388"},{"key":"6828_CR31","doi-asserted-by":"publisher","unstructured":"Villani, C. (2003). Topics in optimal transportation, graduate studies in mathematics (Vol. 58). American Mathematical Society. https:\/\/doi.org\/10.1090\/gsm\/058","DOI":"10.1090\/gsm\/058"},{"key":"6828_CR32","doi-asserted-by":"publisher","unstructured":"Villani, C. (2009). Optimal transport- old and new, fundamental principles of mathematical sciences (vol. 338). Springer-Verlag. https:\/\/doi.org\/10.1007\/978-3-540-71050-9","DOI":"10.1007\/978-3-540-71050-9"},{"key":"6828_CR33","unstructured":"Yang, K., & Uhler, C. (2019). Scalable unbalanced optimal transport using generative adversarial networks. In: 7th international conference on learning representations."},{"issue":"1","key":"6828_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13059-017-1305-0","volume":"18","author":"L Zappia","year":"2017","unstructured":"Zappia, L., Phipson, B., & Oshlack, A. (2017). Splatter: Simulation of single-cell RNA sequencing data. Genome Biology, 18(1), 1\u201315. https:\/\/doi.org\/10.1186\/s13059-017-1305-0","journal-title":"Genome Biology"},{"issue":"12","key":"6828_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1009466","volume":"17","author":"S Zhang","year":"2021","unstructured":"Zhang, S., Afanassiev, A., Greenstreet, L., Matsumoto, T., & Schiebinger, G. (2021). Optimal transport analysis reveals trajectories in steady-state systems. PLOS Computational Biology, 17(12), 1\u201329. https:\/\/doi.org\/10.1371\/journal.pcbi.1009466","journal-title":"PLOS Computational Biology"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06828-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06828-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06828-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T15:48:32Z","timestamp":1754408912000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06828-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,24]]},"references-count":35,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["6828"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06828-8","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2025,7,24]]},"assertion":[{"value":"12 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2025","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 Conflict of interest.","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":"The authors of this article consent to its publication.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"195"}}