{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T21:42:25Z","timestamp":1774042945079,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF","award":["CCF-2046018"],"award-info":[{"award-number":["CCF-2046018"]}]},{"name":"NSF","award":["DMS-2210368"],"award-info":[{"award-number":["DMS-2210368"]}]},{"name":"NSF","award":["CCF-2308446"],"award-info":[{"award-number":["CCF-2308446"]}]},{"name":"International Business Machines Corporation (IBM) Academic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tit.2026.3661439","type":"journal-article","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:48:05Z","timestamp":1770410885000},"page":"2424-2443","source":"Crossref","is-referenced-by-count":0,"title":["Neural Entropic Optimal Transport and Gromov\u2013Wasserstein Alignment"],"prefix":"10.1109","volume":"72","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4379-9312","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Statistics and Data Science, Wharton School, University of Pennsylvania, Philadelphia, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3406-3950","authenticated-orcid":false,"given":"Ziv","family":"Goldfeld","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Cornell University, Ithaca, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.01.006"},{"key":"ref2","first-page":"04","article-title":"Gromov-Wasserstein optimal transport to align single-cell multi-omics data","author":"Demetci","year":"2020","journal-title":"BioRxiv"},{"key":"ref3","article-title":"MREC: A fast and versatile framework for aligning and matching point clouds with applications to single cell molecular data","author":"Blumberg","year":"2020","journal-title":"arXiv:2001.01666"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s43586-024-00334-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457690"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2766963"},{"key":"ref7","first-page":"17755","article-title":"Continuous regularized Wasserstein barycenters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/a16030131"},{"key":"ref9","first-page":"1542","article-title":"Graph optimal transport for cross-domain alignment","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref10","first-page":"13876","article-title":"GOT: An optimal transport framework for graph comparison","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mareti\u0107"},{"key":"ref11","first-page":"6932","article-title":"Gromov-Wasserstein learning for graph matching and node embedding","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Xu"},{"key":"ref12","first-page":"3046","article-title":"Scalable Gromov-Wasserstein learning for graph partitioning and matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Xu"},{"key":"ref13","article-title":"Limit laws for Gromov-Wasserstein alignment with applications to testing graph isomorphisms","author":"Rioux","year":"2024","journal-title":"arXiv:2410.18006"},{"key":"ref14","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref15","article-title":"Wasserstein auto-encoders","author":"Tolstikhin","year":"2017","journal-title":"arXiv:1711.01558"},{"key":"ref16","first-page":"3730","article-title":"Joint distribution optimal transportation for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Courty"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1214"},{"key":"ref18","first-page":"851","article-title":"Learning generative models across incomparable spaces","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bunne"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-025-09722-w"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s00440-014-0583-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1214\/24-AOS2406"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835519"},{"key":"ref23","first-page":"1","article-title":"A survey of the quadratic assignment problem, with applications","volume":"4","author":"Commander","year":"2005","journal-title":"Morehead Electron. J. Applicable Math."},{"key":"ref24","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Cuturi"},{"key":"ref25","first-page":"1574","article-title":"Sample complexity of sinkhorn divergences","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Genevay"},{"key":"ref26","first-page":"4541","article-title":"Statistical bounds for entropic optimal transport: Sample complexity and the central limit theorem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mena"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925903"},{"key":"ref28","first-page":"2664","article-title":"Gromov-Wasserstein averaging of kernel and distance matrices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peyr\u00e9"},{"key":"ref29","article-title":"Lower complexity adaptation for empirical entropic optimal transport","author":"Groppe","year":"2023","journal-title":"arXiv:2306.13580"},{"issue":"363","key":"ref30","first-page":"1","article-title":"Entropic Gromov-Wasserstein distances: Stability and algorithms","volume":"26","author":"Rioux","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2068870"},{"issue":"126","key":"ref32","first-page":"1","article-title":"Neural estimation of statistical divergences","volume":"23","author":"Sreekumar","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1163"},{"key":"ref34","article-title":"Max-sliced mutual information","author":"Tsur","year":"2023","journal-title":"arXiv:2309.16200"},{"key":"ref35","article-title":"On the existence of Monge maps for the Gromov-Wasserstein distance","author":"Dumont","year":"2022","journal-title":"arXiv:2210.11945"},{"key":"ref36","first-page":"12164","article-title":"Entropic Gromov-Wasserstein between Gaussian distributions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Le"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993164"},{"issue":"1","key":"ref38","first-page":"629","article-title":"Breaking the curse of dimensionality with convex neural networks","volume":"18","author":"Bach","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","article-title":"Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: Optimal rate and curse of dimensionality","author":"Suzuki","year":"2018","journal-title":"arXiv:1810.08033"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1017939142"},{"key":"ref41","first-page":"9089","article-title":"Nonparametric density estimation & convergence rates for GANs under Besov IPM losses","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Uppal"},{"key":"ref42","article-title":"MINE: Mutual information neural estimation","author":"Belghazi","year":"2018","journal-title":"arXiv:1801.04062"},{"key":"ref43","first-page":"5171","article-title":"On variational lower bounds of mutual information","volume-title":"Proc. ICML","volume":"97","author":"Poole"},{"key":"ref44","article-title":"Understanding the limitations of variational mutual information estimators","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref45","article-title":"Neural entropic estimation: A faster path to mutual information estimation","author":"Chan","year":"2019","journal-title":"arXiv:1905.12957"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17089"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/e23060641"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3264674"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3335863"},{"key":"ref50","first-page":"3322","article-title":"Non-asymptotic performance guarantees for neural estimation of f-divergences","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"130","author":"Sreekumar"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2023.3299258"},{"key":"ref52","article-title":"Lower bounds for the MMSE via neural network estimation and their applications to privacy","author":"Diaz","year":"2021","journal-title":"arXiv:2108.12851"},{"key":"ref53","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Gulrajani"},{"key":"ref54","first-page":"1","article-title":"Large-scale optimal transport and mapping estimation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Seguy"},{"key":"ref55","first-page":"12955","article-title":"Score-based generative neural networks for large-scale optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Daniels"},{"key":"ref56","article-title":"Energy-guided entropic neural optimal transport","author":"Mokrov","year":"2023","journal-title":"arXiv:2304.06094"},{"key":"ref57","article-title":"Sliced Gromov-Wasserstein","author":"Vayer","year":"2019","journal-title":"arXiv:1905.10124"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/22M1497808"},{"key":"ref59","first-page":"8766","article-title":"The unbalanced Gromov Wasserstein distance: Conic formulation and relaxation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"S\u00e9journ\u00e9"},{"key":"ref60","first-page":"7257","article-title":"Cycle consistent probability divergences across different spaces","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Zhang"},{"key":"ref61","first-page":"19347","article-title":"Linear-time Gromov Wasserstein distances using low rank couplings and costs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Scetbon"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20828-2"},{"key":"ref64","article-title":"Limit theorems for entropic optimal transport maps and the sinkhorn divergence","author":"Goldfeld","year":"2022","journal-title":"arXiv:2207.08683"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9093-5"},{"key":"ref66","article-title":"Empirical optimal transport between different measures adapts to lower complexity","author":"Hundrieser","year":"2022","journal-title":"arXiv:2202.10434"},{"key":"ref67","first-page":"69","article-title":"Neural net approximation","volume-title":"Proc. 7th Yale workshop Adapt. Learn. Syst.","volume":"1","author":"Barron"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/18.256500"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/18.391247"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.oa-2020-0149"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1214\/19-aos1875"},{"key":"ref72","first-page":"10697","article-title":"Sharp representation theorems for ReLU networks with precise dependence on depth","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Bresler"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1070\/SM1967v002n03ABEH002343"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9"},{"key":"ref75","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref76","article-title":"Springer series in statistics","volume-title":"Weak Convergence and Empirical Processes","author":"van der Vaart","year":"1996"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1806579115"},{"key":"ref78","first-page":"3036","article-title":"On the global convergence of gradient descent for over-parameterized models using optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chizat"},{"key":"ref79","first-page":"29736","article-title":"Rates of estimation of optimal transport maps using plug-in estimators via barycentric projections","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deb"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1214\/24-aos2379"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9947-96-01501-2"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/11448285\/11372811-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/11448285\/11372811.pdf?arnumber=11372811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:57:35Z","timestamp":1774036655000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11372811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":81,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tit.2026.3661439","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}