{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T18:40:08Z","timestamp":1787337608186,"version":"build-2736575974"},"reference-count":33,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-19-PI3A-0004"],"award-info":[{"award-number":["ANR-19-PI3A-0004"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR MaSDOL 19-CE23-0017-01"],"award-info":[{"award-number":["ANR MaSDOL 19-CE23-0017-01"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-18-CE40-0005.P"],"award-info":[{"award-number":["ANR-18-CE40-0005.P"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-19-1-7026"],"award-info":[{"award-number":["FA9550-19-1-7026"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA8655-22-1-7012"],"award-info":[{"award-number":["FA8655-22-1-7012"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Optim."],"published-print":{"date-parts":[[2023,9,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>We show that the derivatives of the Sinkhorn\u2013Knopp algorithm, or iterative proportional fitting procedure, converge towards the derivatives of the entropic regularization of the optimal transport problem with a locally uniform linear convergence rate.<\/jats:p>","DOI":"10.1137\/22m1512703","type":"journal-article","created":{"date-parts":[[2023,7,25]],"date-time":"2023-07-25T11:43:59Z","timestamp":1690285439000},"page":"1494-1517","source":"Crossref","is-referenced-by-count":2,"title":["The Derivatives of Sinkhorn\u2013Knopp Converge"],"prefix":"10.1137","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8180-075X","authenticated-orcid":true,"given":"Edouard","family":"Pauwels","sequence":"first","affiliation":[{"name":"IRIT, CNRS, Universit\u00e9 de Toulouse, ANITI, Toulouse, France, and Institut universitaire de France (IUF), 75005, Paris, France."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4077-708X","authenticated-orcid":true,"given":"Samuel","family":"Vaiter","sequence":"additional","affiliation":[{"name":"CNRS & Universit\u00e9 C\u00f4te d\u2019Azur, CNRS, LJAD, Nice, France."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2023,7,24]]},"reference":[{"key":"ref1","unstructured":"R. P. Adams  and \nR. S. Zemel , Ranking via Sinkhorn Propagation, https:\/\/arxiv.org\/abs\/1106.1925, 2011."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/100805741"},{"key":"ref3","series-title":"CMS Books Math. 15","volume-title":"Generalized Inverses: Theory and Applications","author":"Ben-Israel A.","year":"2003","edition":"2"},{"key":"ref4","first-page":"219","volume":"85","author":"Birkhoff G.","year":"1957","journal-title":"Trans. Amer. Math. Soc."},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"J. Bolte , \nE. Pauwels , and \nS. Vaiter , Automatic Differentiation of Nonsmooth Iterative Algorithms, preprint, arXiv:2206.00457, 2022.","DOI":"10.52202\/068431-1915"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925918"},{"key":"ref7","unstructured":"J. Bradbury , \nR. Frostig , \nP. Hawkins , \nM. J. Johnson , \nC. Leary , \nD. Maclaurin , \nG. Necula , \nA. Paszke , \nJ. VanderPlas , \nS. Wanderman-Milne , and \nQ. Zhang , JAX: Composable Transformations of Python+NumPy Programs, 2018, http:\/\/github.com\/google\/jax."},{"key":"ref8","unstructured":"M. Caron , \nI. Misra , \nJ. Mairal , \nP. Goyal , \nP. Bojanowski , and \nA. Joulin , Unsupervised learning of visual features by contrasting cluster assignments, in Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada, Advances in Neural Information Processing Systems 33, Curran Associates, 2020, pp. 9912\u20139924."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/10556789408805572"},{"key":"ref10","unstructured":"M. Cuturi , Sinkhorn distances: Lightspeed computation of optimal transport, in Proceedings of the 27th Annual Conference on Neural Information Processing Systems, Lake Tahoe, NV, Advances in Neural Information Processing Systems 26 (NIPS 2013), Curran Associates, 2013, pp. 2294\u20132302."},{"key":"ref11","unstructured":"M. Cuturi , \nL. Meng-Papaxanthos , \nY. Tian , \nC. Bunne , \nG. Davis , and \nO. Teboul , Optimal Transport Tools (OTT): A Jax Toolbox for All Things Wasserstein, preprint, arXiv:2201.12324, 2022."},{"key":"ref12","unstructured":"M. Cuturi , \nO. Teboul , \nJ. Niles-Weed , and \nJ.P. Vert , Supervised quantile normalization for low-rank matrix approximation, in Proceedings of the 37th International Conference on Machine Learning (ICML \u201920), JMLR.org, 2020, pp. 2269\u20132279."},{"key":"ref13","unstructured":"M. Cuturi , \nO. Teboul , and \nJ.P. Vert , Differentiable ranking and sorting using optimal transport, in Proceedings of the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada, Advances in Neural Information Processing Systems 32, Curran Associates, 2019."},{"key":"ref14","doi-asserted-by":"crossref","unstructured":"M. Eisenberger , \nA. Toker , \nL. Leal-Taix\u00e9 , \nF. Bernard , and \nD. Cremers , A unified framework for implicit sinkhorn differentiation, in Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2022, pp. 499\u2013508.","DOI":"10.1109\/CVPR52688.2022.00059"},{"key":"ref15","first-page":"1","volume":"22","author":"Flamary R.","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(89)90490-4"},{"key":"ref17","unstructured":"A. Genevay , \nG. Peyr\u00e9 , and \nM. Cuturi , Learning generative models with sinkhorn divergences, in Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics (AISTAT), Proceedings of Machine Learning Research 84, JMLR.org, 2018, pp. 1608\u20131617."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/10556789208805503"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/10556789308805549"},{"key":"ref20","unstructured":"T. Hashimoto , \nD. Gifford , and \nT. Jaakkola , Learning population-level diffusions with generative RNNs, in Proceedings of The 33rd International Conference on Machine Learning (ICML), Proceedings of Machine Learning Research 48, JMLR.org, 2016, pp. 2417\u20132426."},{"key":"ref21","volume-title":"Matrix Analysis","author":"Horn R. A.","year":"2013","edition":"2"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/BF01931367"},{"key":"ref23","unstructured":"J. Lorraine , \nP. Vicol , and \nD. Duvenaud , Optimizing millions of hyperparameters by implicit differentiation, in Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), Palermo, Italy. Proceedings of Machine Learning Research 108, JMLR.org, 2020, pp. 1540\u20131552."},{"key":"ref24","unstructured":"G. Luise , \nA. Rudi , \nM. Pontil , and \nC. Ciliberto , Differential properties of sinkhorn approximation for learning with Wasserstein distance, in Proceedings of the 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montr\u00e9al, Canada, Advances in Neural Information Processing Systems 31, Curran Associates, 2018, pp. 5864\u20135874."},{"key":"ref25","unstructured":"S. Mehmood  and \nP. Ochs , Automatic differentiation of some first-order methods in parametric optimization, in Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) Palermo, Italy, Proceedings of Machine Learning Research 108, JMLR.org, 2020, pp. 1584\u20131594."},{"key":"ref26","first-page":"1","volume":"51","author":"Peyr\u00e9 G.","year":"2019","journal-title":"Found. Trends Mach. Learn."},{"key":"ref27","unstructured":"B. Polyak , Introduction to Optimization, Optimization Software, 1987."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176324703"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1137\/0114067"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703591"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2307\/2314570"},{"key":"ref32","unstructured":"J. Thornton  and \nM. Cuturi , Rethinking Initialization of the Sinkhorn Algorithm, https:\/\/doi.org\/10.48550\/ARXIV.2206.07630, 2022."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/355586.364791"}],"container-title":["SIAM Journal on Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/22M1512703","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T18:20:17Z","timestamp":1787336417000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/22M1512703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,24]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9,30]]}},"alternative-id":["10.1137\/22M1512703"],"URL":"https:\/\/doi.org\/10.1137\/22m1512703","relation":{},"ISSN":["1052-6234","1095-7189"],"issn-type":[{"value":"1052-6234","type":"print"},{"value":"1095-7189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,24]]}}}