{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T19:41:26Z","timestamp":1787341286890,"version":"build-2736575974"},"reference-count":51,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"2","funder":[{"name":"Cluster of Excellence","award":["EXC 2064\/1 390727645"],"award-info":[{"award-number":["EXC 2064\/1 390727645"]}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["553088969"],"award-info":[{"award-number":["553088969"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Optim."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Motivated by the success of Sinkhorn\u2019s algorithm for entropic optimal transport, we study convergence properties of iterative proportional fitting procedures (IPFP) used to solve more general information projection problems. We establish exponential convergence guarantees for the IPFP whenever the set of probability measures which is projected onto is defined through constraints arising from linear function spaces. This unifies and extends recent results from multimarginal, adapted,\u00a0and martingale optimal transport. The proofs are based on strong convexity arguments for the dual problem, and the key contribution is to illuminate the role of the geometric interplay between the subspaces defining the constraints. In this regard, we show that the larger the angle (in the sense of Friedrichs) between the linear function spaces, the better the rate of contraction of the IPFP.<\/jats:p>","DOI":"10.1137\/25m1752584","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T07:34:10Z","timestamp":1779867250000},"page":"912-937","source":"Crossref","is-referenced-by-count":0,"title":["Exponential Convergence of General Iterative Proportional Fitting Procedures"],"prefix":"10.1137","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6407-2498","authenticated-orcid":true,"given":"Stephan","family":"Eckstein","sequence":"first","affiliation":[{"name":"Department of Mathematics, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aziz","family":"Lakhal","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"ref1","unstructured":"M. Arnese and D. Lacker, Convergence of Coordinate Ascent Variational Inference for Log-Concave Measures via Optimal Transport, preprint, https:\/\/arxiv.org\/abs\/2404.08792, 2024."},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080197"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3221286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOP966"},{"key":"ref5","unstructured":"P. Bellec and T. Fritz, Optimizing over iid Distributions and the Beat the Average Game, preprint, https:\/\/arxiv.org\/abs\/2412.15179, 2024."},{"key":"ref6","unstructured":"J.D. Benamou, G. Chazareix, M. Hoffmann, G. Loeper, and F.X. Vialard, Entropic Semi-Martingale Optimal Transport, preprint, https:\/\/arxiv.org\/abs\/2408.09361, 2024."},{"key":"ref7","unstructured":"C. Bunne, L. Papaxanthos, A. Krause, and M. Cuturi, Proximal optimal transport modeling of population dynamics, in International Conference on Artificial Intelligence and Statistics, PMLR, 2022, pp. 6511\u20136528, https:\/\/proceedings.mlr.press\/v151\/bunne22a\/bunne22a.pdf."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-022-01728-4"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/21M1410634"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1137\/15M1050264"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"F. Chen, G. Conforti, Z. Ren, and X. Wang, Convergence of Sinkhorn\u2019s algorithm for entropic martingale optimal transport problem, Math. Oper. Res. (2026), https:\/\/doi.org\/10.1287\/moor.2024.0619.","DOI":"10.1287\/moor.2024.0619"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/16M1061382"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3150\/24-BEJ1773"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1137\/16M1064088"},{"key":"ref15","unstructured":"A. Chiarini, G. Conforti, G. Greco, and L. Tamanini, A Semiconcavity Approach to Stability of Entropic Plans and Exponential Convergence of Sinkhorn\u2019s Algorithm, preprint, https:\/\/arxiv.org\/abs\/2412.09235, 2024."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-025-02242-z"},{"key":"ref17","unstructured":"G. Conforti, A. Durmus, and G. Greco, Quantitative Contraction Rates for Sinkhorn Algorithm: Beyond Bounded Costs and Compact Marginals, preprint, https:\/\/arxiv.org\/abs\/2304.04451, 2023."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176996454"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.810633"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3501335"},{"key":"ref21","volume-title":"Advances in Neural Information Processing Systems","volume":"26","author":"Cuturi M.","year":"2013"},{"key":"ref22","first-page":"17695","volume-title":"Advances in Neural Information Processing Systems, Vol. 34","author":"De Bortoli V.","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2016.04.009"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1089\/cmb.2021.0446"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177731829"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-8577-4_7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1214\/aop\/1176992918"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-025-01366-9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s00245-019-09558-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1214\/23-AAP1975"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177696968"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-1937-1501907-0"},{"key":"ref33","first-page":"1","volume":"25","author":"Fr\u00f6hlich C.","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"Z. Ge, S. Liu, Z. Li, O. Yoshie, and J. Sun, OTA: Optimal transport assignment for object detection, in 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, New York, 2021, pp. 303\u2013312, https:\/\/doi.org\/10.1109\/CVPR46437.2021.00037.","DOI":"10.1109\/CVPR46437.2021.00037"},{"key":"ref35","unstructured":"A. Genevay, G. Peyr\u00e9, and M. Cuturi, Learning generative models with Sinkhorn divergences, in International Conference on Artificial Intelligence and Statistics, PMLR, 2018, pp. 1608\u20131617."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0103945"},{"key":"ref37","author":"Hu Z.","year":"2012","journal-title":"Optimization Online"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0883"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"E. Lei, H. Hassani, and S. S. Bidokhti, Neural estimation of the rate-distortion function for massive datasets, in 2022 IEEE International Symposium on Information Theory (ISIT), IEEE, New York, 2022, pp. 608\u2013613.","DOI":"10.1109\/ISIT50566.2022.9834845"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfa.2011.11.026"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-017-1172-1"},{"key":"ref42","volume-title":"Introduction to Entropic Optimal Transport","author":"Nutz M.","year":"2022"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref44","unstructured":"A.A. Pooladian and J. Niles-Weed, Entropic Estimation of Optimal Transport Maps, preprint, https:\/\/arxiv.org\/abs\/2109.12004, 2021."},{"key":"ref45","volume":"3","author":"Rahimian H.","year":"2022","journal-title":"Open J. Math. Optim."},{"key":"ref46","volume-title":"Functional Analysis","author":"Rudin W.","year":"1991"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176324703"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.2307\/2314570"},{"key":"ref49","unstructured":"J. von Lindheim and G. Steidl, Generalized Iterative Scaling for Regularized Optimal Transport with Affine Constraints:\u00a0Application Examples, preprint, https:\/\/arxiv.org\/abs\/2305.07071, 2023."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1134\/S0001434615110036"},{"key":"ref51","doi-asserted-by":"crossref","unstructured":"T. Zhou, W. Wang, E. Konukoglu, and L. Van Gool, Rethinking semantic segmentation: A prototype view, in 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, New York, 2022, pp. 2582\u20132593, https:\/\/doi.org\/10.1109\/CVPR52688.2022.00261.","DOI":"10.1109\/CVPR52688.2022.00261"}],"container-title":["SIAM Journal on Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/25M1752584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T19:12:44Z","timestamp":1787339564000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/25M1752584"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":51,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1137\/25M1752584"],"URL":"https:\/\/doi.org\/10.1137\/25m1752584","relation":{},"ISSN":["1052-6234","1095-7189"],"issn-type":[{"value":"1052-6234","type":"print"},{"value":"1095-7189","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]}}}