乐胖代购免代理版

{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T15:23:38Z","timestamp":1726413818279},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006764","name":"Technische Universit\u00e4t Berlin","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006764","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Comput Optim Appl"],"published-print":{"date-parts":[[2023,5]]},"abstract":"Abstract<\/jats:title>Computing Wasserstein barycenters of discrete measures has recently attracted considerable attention due to its wide variety of applications in data science. In general, this problem is NP-hard, calling for practical approximative algorithms. In this paper, we analyze a well-known simple framework for approximating Wasserstein-

$${\\varvec{p}}$$<\/jats:tex-math>p<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>barycenters, where we mainly consider the most common case

$${\\varvec{p}}={\\varvec{2}}$$<\/jats:tex-math>p<\/mml:mi><\/mml:mrow>=<\/mml:mo>2<\/mml:mn><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>and

$${\\varvec{p}}={\\varvec{1}}$$<\/jats:tex-math>p<\/mml:mi><\/mml:mrow>=<\/mml:mo>1<\/mml:mn><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>, which is not as well discussed. The framework produces sparse support solutions and shows good numerical results in the free-support setting. Depending on the desired level of accuracy, this requires only

$${\\varvec{N}}-{\\varvec{1}}$$<\/jats:tex-math>N<\/mml:mi><\/mml:mrow>-<\/mml:mo>1<\/mml:mn><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>or

$${\\varvec{N(N}}-{\\varvec{1)\/2 }}$$<\/jats:tex-math>N<\/mml:mi>(<\/mml:mo>N<\/mml:mi><\/mml:mrow>-<\/mml:mo>1<\/mml:mn>)<\/mml:mo>\/<\/mml:mo>2<\/mml:mn><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>standard two-marginal optimal transport (OT) computations between the

$${\\varvec{N}}$$<\/jats:tex-math>N<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>input measures, respectively, which is fast, memory-efficient and easy to implement using any OT solver as a black box. What is more, these methods yield a relative error of at most

$${\\varvec{N}}$$<\/jats:tex-math>N<\/mml:mi><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>and

$${\\varvec{2}}$$<\/jats:tex-math>2<\/mml:mn><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>, respectively, for both

$${\\varvec{p}}={\\varvec{ 1, 2}}$$<\/jats:tex-math>p<\/mml:mi><\/mml:mrow>=<\/mml:mo>1<\/mml:mn>,<\/mml:mo>2<\/mml:mn><\/mml:mrow><\/mml:mrow><\/mml:math><\/jats:alternatives><\/jats:inline-formula>. We show that these bounds are practically sharp. In light of the hardness of the problem, it is not surprising that such guarantees cannot be close to optimality in general. Nevertheless, these error bounds usually turn out to be drastically lower for a given particular problem in practice and can be evaluated with almost no computational overhead, in particular without knowledge of the optimal solution. In our numerical experiments, this guaranteed errors of at most a few percent.<\/jats:p>","DOI":"10.1007\/s10589-023-00458-3","type":"journal-article","created":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T16:03:21Z","timestamp":1677686601000},"page":"213-246","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Simple approximative algorithms for free-support Wasserstein barycenters"],"prefix":"10.1007","volume":"85","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9876-8410","authenticated-orcid":false,"given":"Johannes von","family":"Lindheim","sequence":"first","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,1]]},"reference":[{"issue":"2","key":"458_CR1","doi-asserted-by":"publisher","first-page":"904","DOI":"10.1137\/100805741","volume":"43","author":"M Agueh","year":"2011","unstructured":"Agueh, M., Carlier, G.: Barycenters in the Wasserstein space. SIAM J. Math. Anal. 43(2), 904\u2013924 (2011). https:\/\/doi.org\/10.1137\/100805741","journal-title":"SIAM J. Math. Anal."},{"key":"458_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2019.104581","volume":"176","author":"G Puccetti","year":"2020","unstructured":"Puccetti, G., R\u00fcschendorf, L., Vanduffel, S.: On the computation of Wasserstein barycenters. J. Multivariate Anal. 176, 104581 (2020). https:\/\/doi.org\/10.1016\/j.jmva.2019.104581","journal-title":"J. Multivariate Anal."},{"issue":"1","key":"458_CR3","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s00454-014-9604-7","volume":"52","author":"K Turner","year":"2014","unstructured":"Turner, K., Mileyko, Y., Mukherjee, S., Harer, J.: Fr\u00e9chet means for distributions of persistence diagrams. Discrete Comput. Geom. 52(1), 44\u201370 (2014). https:\/\/doi.org\/10.1007\/s00454-014-9604-7","journal-title":"Discrete Comput. Geom."},{"issue":"1","key":"458_CR4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1137\/S0036141002404838","volume":"37","author":"A Trouv\u00e9","year":"2005","unstructured":"Trouv\u00e9, A., Younes, L.: Local geometry of deformable templates. SIAM J. Math. Anal. 37(1), 17\u201359 (2005). https:\/\/doi.org\/10.1137\/S0036141002404838","journal-title":"SIAM J. Math. Anal."},{"issue":"2","key":"458_CR5","doi-asserted-by":"publisher","first-page":"932","DOI":"10.3150\/17-bej1009","volume":"25","author":"Y Zemel","year":"2019","unstructured":"Zemel, Y., Panaretos, V.M.: Fr\u00e9chet means and Procrustes analysis in Wasserstein space. Bernoulli 25(2), 932\u2013976 (2019). https:\/\/doi.org\/10.3150\/17-bej1009","journal-title":"Bernoulli"},{"key":"458_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-022-01108-9","author":"A Houdard","year":"2022","unstructured":"Houdard, A., Leclaire, A., Papadakis, N., Rabin, J.: A generative model for texture synthesis based on optimal transport between feature distributions. J. Math. Imaging Vis. (2022). https:\/\/doi.org\/10.1007\/s10851-022-01108-9","journal-title":"J. Math. Imaging Vis."},{"key":"458_CR7","doi-asserted-by":"crossref","unstructured":"Rabin, J., Peyr\u00e9, G., Delon, J., Bernot, M.: Wasserstein barycenter and its application to texture mixing. In: international conference on scale space and variational methods in computer vision, pp 435\u2013446 (2011). Springer","DOI":"10.1007\/978-3-642-24785-9_37"},{"key":"458_CR8","doi-asserted-by":"publisher","unstructured":"Bonneel, N., van\u00a0de Panne, M., Paris, S., Heidrich, W.: Displacement interpolation using Lagrangian mass transport. In: Proceedings of the 2011 SIGGRAPH Asia Conference. SA \u201911. association for computing machinery, New York, NY, USA (2011). https:\/\/doi.org\/10.1145\/2024156.2024192","DOI":"10.1145\/2024156.2024192"},{"issue":"4","key":"458_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2766963","volume":"34","author":"J Solomon","year":"2015","unstructured":"Solomon, J., de Goes, F., Peyr\u00e9, G., Cuturi, M., Butscher, A., Nguyen, A., Du, T., Guibas, L.: Convolutional Wasserstein distances: efficient optimal transportation on geometric domains. ACM Trans. Graph. 34(4), 1\u201311 (2015). https:\/\/doi.org\/10.1145\/2766963","journal-title":"ACM Trans. Graph."},{"key":"458_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2020.107474","volume":"171","author":"F Elvander","year":"2020","unstructured":"Elvander, F., Haasler, I., Jakobsson, A., Karlsson, J.: Multi-marginal optimal transport using partial information with applications in robust localization and sensor fusion. Signal Process. 171, 107474 (2020). https:\/\/doi.org\/10.1016\/j.sigpro.2020.107474","journal-title":"Signal Process."},{"key":"458_CR11","first-page":"8","volume":"19","author":"S Srivastava","year":"2018","unstructured":"Srivastava, S., Li, C., Dunson, D.B.: Scalable Bayes via barycenter in Wasserstein space. J. Mach. Learn. Res. 19, 8\u201335 (2018)","journal-title":"J. Mach. Learn. Res."},{"key":"458_CR12","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1146\/annurev-statistics-030718-104938","volume":"6","author":"VM Panaretos","year":"2019","unstructured":"Panaretos, V.M., Zemel, Y.: Statistical aspects of Wasserstein distances. Annu. Rev. Stat. Appl. 6, 405\u2013431 (2019). https:\/\/doi.org\/10.1146\/annurev-statistics-030718-104938","journal-title":"Annu. Rev. Stat. Appl."},{"issue":"5\u20136","key":"458_CR13","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., et al.: Computational optimal transport: with applications to data science. Found. Trends Mach. Learn. 11(5\u20136), 355\u2013607 (2019)","journal-title":"Found. Trends Mach. Learn."},{"issue":"1","key":"458_CR14","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1137\/21M1390062","volume":"4","author":"JM Altschuler","year":"2022","unstructured":"Altschuler, J.M., Boix-Adser\u00e0, E.: Wasserstein barycenters are NP-hard to compute. SIAM J. Math. Data Sci. 4(1), 179\u2013203 (2022). https:\/\/doi.org\/10.1137\/21M1390062","journal-title":"SIAM J. Math. Data Sci."},{"key":"458_CR15","unstructured":"Cuturi, M., Doucet, A.: Fast computation of Wasserstein barycenters. In: international conference on machine learning, pp. 685\u2013693 (2014). PMLR"},{"issue":"2","key":"458_CR16","doi-asserted-by":"publisher","first-page":"1111","DOI":"10.1137\/141000439","volume":"37","author":"J-D Benamou","year":"2015","unstructured":"Benamou, J.-D., Carlier, G., Cuturi, M., Nenna, L., Peyr\u00e9, G.: Iterative Bregman projections for regularized transportation problems. SIAM J. Sci. Comput. 37(2), 1111\u20131138 (2015). https:\/\/doi.org\/10.1137\/141000439","journal-title":"SIAM J. Sci. Comput."},{"key":"458_CR17","unstructured":"Kroshnin, A., Tupitsa, N., Dvinskikh, D., Dvurechensky, P., Gasnikov, A., Uribe, C.: On the complexity of approximating Wasserstein barycenters. In: Chaudhuri, K., Salakhutdinov, R. (eds.) proceedings of the 36th international conference on machine learning. Proceedings of Machine Learning Research, vol. 97, pp. 3530\u20133540. PMLR, Long Beach, California, USA (2019). https:\/\/proceedings.mlr.press\/v97\/kroshnin19a.html"},{"key":"458_CR18","unstructured":"Ge, D., Wang, H., Xiong, Z., Ye, Y.: Interior-point methods strike back: Solving the Wasserstein barycenter problem. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in neural information processing systems, vol. 32. Curran Associates, Inc., Vancouver Convention Center, Vancouver, CA (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/0937fb5864ed06ffb59ae5f9b5ed67a9-Paper.pdf"},{"issue":"21","key":"458_CR19","first-page":"1","volume":"22","author":"L Yang","year":"2021","unstructured":"Yang, L., Li, J., Sun, D., Toh, K.-C.: A fast globally linearly convergent algorithm for the computation of Wasserstein barycenters. J. Mach. Learn. Res. 22(21), 1\u201337 (2021)","journal-title":"J. Mach. Learn. Res."},{"issue":"65","key":"458_CR20","first-page":"1","volume":"23","author":"T Lin","year":"2022","unstructured":"Lin, T., Ho, N., Cuturi, M., Jordan, M.I.: On the complexity of approximating multimarginal optimal transport. J. Mach. Learn. Res. 23(65), 1\u201343 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"458_CR21","unstructured":"Janati, H., Cuturi, M., Gramfort, A.: Debiased Sinkhorn barycenters. In: III, H.D., Singh, A. (eds.) Proceedings of the 37th international conference on machine learning. Proceedings of machine learning research, vol. 119, pp. 4692\u20134701. PMLR, virtual (2020). http:\/\/proceedings.mlr.press\/v119\/janati20a.html"},{"key":"458_CR22","unstructured":"Takezawa, Y., Sato, R., Kozareva, Z., Ravi, S., Yamada, M.: Fixed support tree-sliced Wasserstein barycenter. In: Camps-Valls, G., Ruiz, F.J.R., Valera, I. (eds.) Proceedings of the 25th international conference on artificial intelligence and statistics. Proceedings of Machine Learning Research, vol. 151, pp. 1120\u20131137. PMLR, virtual (2022). https:\/\/proceedings.mlr.press\/v151\/takezawa22a.html"},{"key":"458_CR23","unstructured":"Lin, T., Ho, N., Chen, X., Cuturi, M., Jordan, M.: Fixed-support Wasserstein barycenters: Computational hardness and fast algorithm. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in neural information processing systems, vol. 33, pp. 5368\u20135380. Curran Associates, Inc., virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/3a029f04d76d32e79367c4b3255dda4d-Paper.pdf"},{"key":"458_CR24","unstructured":"Dvinskikh, D., Tiapkin, D.: Improved complexity bounds in Wasserstein barycenter problem. In: International conference on artificial intelligence and statistics, pp. 1738\u20131746 (2021). PMLR"},{"issue":"1","key":"458_CR25","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1002\/(SICI)1097-0312(199801)51:1<23::AID-CPA2>3.0.CO;2-H","volume":"51","author":"W Gangbo","year":"1998","unstructured":"Gangbo, W., \u015awi\u0229ch, A.: Optimal maps for the multidimensional Monge-Kantorovich problem. Comm. Pure Appl. Math. 51(1), 23\u201345 (1998). https:\/\/doi.org\/10.1002\/(SICI)1097-0312(199801)51:1<23::AID-CPA2>3.0.CO;2-H","journal-title":"Comm. Pure Appl. Math."},{"issue":"1","key":"458_CR26","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s00211-018-0995-x","volume":"142","author":"J-D Benamou","year":"2019","unstructured":"Benamou, J.-D., Carlier, G., Nenna, L.: Generalized incompressible flows, multi-marginal transport and Sinkhorn algorithm. Numer. Math. 142(1), 33\u201354 (2019). https:\/\/doi.org\/10.1007\/s00211-018-0995-x","journal-title":"Numer. Math."},{"issue":"4","key":"458_CR27","doi-asserted-by":"publisher","first-page":"2428","DOI":"10.1137\/20M1320195","volume":"59","author":"I Haasler","year":"2021","unstructured":"Haasler, I., Ringh, A., Chen, Y., Karlsson, J.: Multimarginal optimal transport with a tree-structured cost and the Schr\u00f6dinger bridge problem. SIAM J. Control Optim. 59(4), 2428\u20132453 (2021). https:\/\/doi.org\/10.1137\/20M1320195","journal-title":"SIAM J. Control Optim."},{"key":"458_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-022-01126-7","author":"F Beier","year":"2022","unstructured":"Beier, F., von Lindheim, J., Neumayer, S., Steidl, G.: Unbalanced multi-marginal optimal transport. J. Math. Imaging Vis. (2022). https:\/\/doi.org\/10.1007\/s10851-022-01126-7","journal-title":"J. Math. Imaging Vis."},{"issue":"2","key":"458_CR29","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/s00186-016-0549-x","volume":"84","author":"E Anderes","year":"2016","unstructured":"Anderes, E., Borgwardt, S., Miller, J.: Discrete Wasserstein barycenters: optimal transport for discrete data. Math. Methods Oper. Res. 84(2), 389\u2013409 (2016). https:\/\/doi.org\/10.1007\/s00186-016-0549-x","journal-title":"Math. Methods Oper. Res."},{"issue":"44","key":"458_CR30","first-page":"1","volume":"22","author":"JM Altschuler","year":"2021","unstructured":"Altschuler, J.M., Boix-Adsera, E.: Wasserstein barycenters can be computed in polynomial time in fixed dimension. J. Mach. Learn. Res. 22(44), 1\u201319 (2021)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"458_CR31","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1287\/ijoo.2019.0020","volume":"2","author":"S Borgwardt","year":"2020","unstructured":"Borgwardt, S., Patterson, S.: Improved linear programs for discrete barycenters. INFORMS J. Optim. 2(1), 14\u201333 (2020). https:\/\/doi.org\/10.1287\/ijoo.2019.0020","journal-title":"INFORMS J. Optim."},{"key":"458_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.disopt.2021.100674","volume":"43","author":"S Borgwardt","year":"2022","unstructured":"Borgwardt, S., Patterson, S.: A column generation approach to the discrete barycenter problem. Discrete Optim. 43, 100674 (2022). https:\/\/doi.org\/10.1016\/j.disopt.2021.100674","journal-title":"Discrete Optim."},{"issue":"2","key":"458_CR33","first-page":"1511","volume":"22","author":"S Borgwardt","year":"2020","unstructured":"Borgwardt, S.: An lp-based, strongly-polynomial 2-approximation algorithm for sparse Wasserstein barycenters. Oper. Res. 22(2), 1511\u20131551 (2020)","journal-title":"Oper. Res."},{"issue":"2","key":"458_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40314-020-01395-1","volume":"40","author":"Y Qian","year":"2021","unstructured":"Qian, Y., Pan, S.: An inexact PAM method for computing Wasserstein barycenter with unknown supports. Comput. Appl. Math. 40(2), 1\u201329 (2021). https:\/\/doi.org\/10.1007\/s40314-020-01395-1","journal-title":"Comput. Appl. Math."},{"key":"458_CR35","unstructured":"Claici, S., Chien, E., Solomon, J.: Stochastic Wasserstein barycenters. In: Dy, J., Krause, A. (eds.) In: Proceedings of the 35th international conference on machine learning. proceedings of machine learning research, vol. 80, pp. 999\u20131008. PMLR, Stockholmsm\u00e4ssan, Stockholm, SE (2018). https:\/\/proceedings.mlr.press\/v80\/claici18a.html"},{"key":"458_CR36","unstructured":"Luise, G., Salzo, S., Pontil, M., Ciliberto, C.: Sinkhorn barycenters with free support via Frank\u2013Wolfe algorithm. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in neural information processing systems, vol. 32, pp. 9322\u20139333. Curran Associates, Inc., Vancouver Convention Center, Vancouver, CA (2019). https:\/\/proceedings.neurips.cc\/paper\/2019\/file\/9f96f36b7aae3b1ff847c26ac94c604e-Paper.pdf"},{"key":"458_CR37","unstructured":"Li, L., Genevay, A., Yurochkin, M., Solomon, J.M.: Continuous regularized Wasserstein barycenters. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 17755\u201317765. Curran Associates, Inc., virtual (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/cdf1035c34ec380218a8cc9a43d438f9-Paper.pdf"},{"key":"458_CR38","unstructured":"von Lindheim, J.: Approximative algorithms for multi-marginal optimal transport and free-support wasserstein barycenters. arXiv preprint arXiv:2202.00954 (2022)"},{"issue":"1","key":"458_CR39","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1137\/20M1385263","volume":"4","author":"F Heinemann","year":"2022","unstructured":"Heinemann, F., Munk, A., Zemel, Y.: Randomized Wasserstein barycenter computation: resampling with statistical guarantees. SIAM J. Math. Data Sci. 4(1), 229\u2013259 (2022). https:\/\/doi.org\/10.1137\/20M1385263","journal-title":"SIAM J. Math. Data Sci."},{"key":"458_CR40","unstructured":"Izzo, Z., Silwal, S., Zhou, S.: Dimensionality reduction for Wasserstein barycenter. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=cDPFOsj2G6B"},{"issue":"2","key":"458_CR41","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/s00199-008-0415-z","volume":"42","author":"G Carlier","year":"2010","unstructured":"Carlier, G., Ekeland, I.: Matching for teams. Econom. Theory 42(2), 397\u2013418 (2010). https:\/\/doi.org\/10.1007\/s00199-008-0415-z","journal-title":"Econom. Theory"},{"key":"458_CR42","doi-asserted-by":"crossref","unstructured":"Friesecke, G., Penka, M.: The GenCol algorithm for high-dimensional optimal transport: general formulation and application to barycenters and Wasserstein splines. arXiv preprint arXiv:2209.09081 (2022)","DOI":"10.1137\/22M1524254"},{"key":"458_CR43","unstructured":"Ambrosio, L., Gigli, N., Savar\u00e9, G.: Gradient flows in metric spaces and in the space of probability measures, 2nd edn. Lectures in Mathematics ETH Z\u00fcrich, p. 334. Birkh\u00e4user Verlag, Basel, Basel, CH (2008)"},{"key":"458_CR44","doi-asserted-by":"publisher","first-page":"7292","DOI":"10.1109\/TIP.2022.3221286","volume":"31","author":"F Beier","year":"2022","unstructured":"Beier, F., Beinert, R., Steidl, G.: On a linear Gromov-Wasserstein distance. IEEE Trans. Image Process. 31, 7292\u20137305 (2022). https:\/\/doi.org\/10.1109\/TIP.2022.3221286","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"458_CR45","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1137\/21M1400080","volume":"15","author":"T Cai","year":"2022","unstructured":"Cai, T., Cheng, J., Schmitzer, B., Thorpe, M.: The linearized Hellinger-Kantorovich distance. SIAM J. Imaging Sci. 15(1), 45\u201383 (2022). https:\/\/doi.org\/10.1137\/21M1400080","journal-title":"SIAM J. Imaging Sci."},{"issue":"2","key":"458_CR46","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/s11263-012-0566-z","volume":"101","author":"W Wang","year":"2013","unstructured":"Wang, W., Slep\u010dev, D., Basu, S., Ozolek, J.A., Rohde, G.K.: A linear optimal transportation framework for quantifying and visualizing variations in sets of images. Int. J. Comput. Vis. 101(2), 254\u2013269 (2013)","journal-title":"Int. J. Comput. Vis."},{"key":"458_CR47","unstructured":"M\u00e9rigot, Q., Delalande, A., Chazal, F.: Quantitative stability of optimal transport maps and linearization of the 2-Wasserstein space. In: Chiappa, S., Calandra, R. (eds.) In: Proceedings of the twenty third international conference on artificial intelligence and statistics. proceedings of machine learning research, vol. 108, pp. 3186\u20133196. PMLR, virtual (2020). https:\/\/proceedings.mlr.press\/v108\/merigot20a.html"},{"key":"458_CR48","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaac023","author":"C Moosm\u00fcller","year":"2022","unstructured":"Moosm\u00fcller, C., Cloninger, A.: Linear optimal transport embedding: provable Wasserstein classification for certain rigid transformations and perturbations. Inf. Inference (2022). https:\/\/doi.org\/10.1093\/imaiai\/iaac023","journal-title":"Inf. Inference"},{"issue":"2","key":"458_CR49","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1016\/j.jmaa.2016.04.045","volume":"441","author":"PC \u00c1lvarez-Esteban","year":"2016","unstructured":"\u00c1lvarez-Esteban, P.C., del Barrio, E., Cuesta-Albertos, J.A., Matr\u00e1n, C.: A fixed-point approach to barycenters in Wasserstein space. J. Math. Anal. Appl. 441(2), 744\u2013762 (2016). https:\/\/doi.org\/10.1016\/j.jmaa.2016.04.045","journal-title":"J. Math. Anal. Appl."},{"key":"458_CR50","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1051\/ps\/2017020","volume":"22","author":"J Bigot","year":"2018","unstructured":"Bigot, J., Klein, T.: Characterization of barycenters in the Wasserstein space by averaging optimal transport maps. ESAIM Probab. Stat. 22, 35\u201357 (2018). https:\/\/doi.org\/10.1051\/ps\/2017020","journal-title":"ESAIM Probab. Stat."},{"key":"458_CR51","unstructured":"Cazelles, E., Tobar, F., Fontbona, J.: A novel notion of barycenter for probability distributions based on optimal weak mass transport. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P.S., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol. 34, pp. 13575\u201313586. Curran Associates, Inc., virtual (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/70d5212dd052b2ef06e5e562f6f9ab9c-Paper.pdf"},{"issue":"1","key":"458_CR52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10957-014-0586-7","volume":"164","author":"A Beck","year":"2015","unstructured":"Beck, A., Sabach, S.: Weiszfeld\u2019s method: old and new results. J. Optim. Theory Appl. 164(1), 1\u201340 (2015). https:\/\/doi.org\/10.1007\/s10957-014-0586-7","journal-title":"J. Optim. Theory Appl."},{"issue":"2","key":"458_CR53","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/BF02187906","volume":"3","author":"C Bajaj","year":"1988","unstructured":"Bajaj, C.: The algebraic degree of geometric optimization problems. Discrete Comput. Geom. 3(2), 177\u2013191 (1988). https:\/\/doi.org\/10.1007\/BF02187906","journal-title":"Discrete Comput. Geom."},{"key":"458_CR54","doi-asserted-by":"publisher","unstructured":"Santambrogio, F.: Optimal Transport for Applied Mathematicians. Progress in Nonlinear Differential Equations and their Applications, vol. 87, p. 353. Birkh\u00e4user\/Springer, Cham, Cham, CH (2015). https:\/\/doi.org\/10.1007\/978-3-319-20828-2. Calculus of variations, PDEs, and modeling","DOI":"10.1007\/978-3-319-20828-2"},{"issue":"78","key":"458_CR55","first-page":"1","volume":"22","author":"R Flamary","year":"2021","unstructured":"Flamary, R., Courty, N., Gramfort, A., Alaya, M.Z., Boisbunon, A., Chambon, S., Chapel, L., Corenflos, A., Fatras, K., Fournier, N., Gautheron, L., Gayraud, N.T.H., Janati, H., Rakotomamonjy, A., Redko, I., Rolet, A., Schutz, A., Seguy, V., Sutherland, D.J., Tavenard, R., Tong, A., Vayer, T.: Pot: Python optimal transport. J. Mach. Learn. Res. 22(78), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"issue":"9","key":"458_CR56","doi-asserted-by":"publisher","first-page":"2317","DOI":"10.1109\/TSP.2017.2659647","volume":"65","author":"J Ye","year":"2017","unstructured":"Ye, J., Wu, P., Wang, J.Z., Li, J.: Fast discrete distribution clustering using Wasserstein barycenter with sparse support. IEEE Trans. Signal Process. 65(9), 2317\u20132332 (2017). https:\/\/doi.org\/10.1109\/TSP.2017.2659647","journal-title":"IEEE Trans. Signal Process."},{"issue":"1","key":"458_CR57","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1214\/aos\/1176347978","volume":"19","author":"HP Lopuha\u00e4","year":"1991","unstructured":"Lopuha\u00e4, H.P., Rousseeuw, P.J.: Breakdown points of affine equivariant estimators of multivariate location and covariance matrices. Ann. Statist. 19(1), 229\u2013248 (1991). https:\/\/doi.org\/10.1214\/aos\/1176347978","journal-title":"Ann. Statist."},{"key":"458_CR58","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., , Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conf. on computer vision and pattern recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"458_CR59","doi-asserted-by":"publisher","unstructured":"Welzl, E.: Smallest enclosing disks (balls and ellipsoids). In: new results and new trends in computer science (Graz, 1991). Lecture Notes in Comput. Sci., vol. 555, pp. 359\u2013370. Springer, Graz, AT (1991). https:\/\/doi.org\/10.1007\/BFb0038202","DOI":"10.1007\/BFb0038202"}],"container-title":["Computational Optimization and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-023-00458-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10589-023-00458-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10589-023-00458-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T02:26:18Z","timestamp":1702002378000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10589-023-00458-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["458"],"URL":"https:\/\/doi.org\/10.1007\/s10589-023-00458-3","relation":{},"ISSN":["0926-6003","1573-2894"],"issn-type":[{"type":"print","value":"0926-6003"},{"type":"electronic","value":"1573-2894"}],"subject":[],"published":{"date-parts":[[2023,3,1]]},"assertion":[{"value":"9 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2023","order":3,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}