{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T21:36:36Z","timestamp":1780695396787,"version":"3.54.1"},"reference-count":176,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tpami.2024.3489030","type":"journal-article","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T17:34:05Z","timestamp":1730396045000},"page":"1161-1180","source":"Crossref","is-referenced-by-count":37,"title":["Recent Advances in Optimal Transport for Machine Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3850-4602","authenticated-orcid":false,"given":"Eduardo Fernandes","family":"Montesuma","sequence":"first","affiliation":[{"name":"Université Paris-Saclay, CEA, LIST, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fred Maurice Ngol\u00e8","family":"Mboula","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay, CEA, LIST, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine","family":"Souloumiac","sequence":"additional","affiliation":[{"name":"Université Paris-Saclay, CEA, LIST, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"M\u00e9moire sur la th\u00e9orie des d\u00e9blais et des remblais","author":"Monge","year":"1781"},{"issue":"2","key":"ref2","first-page":"227","article-title":"On the transfer of masses (in Russian)","volume":"37","author":"Kantorovich","year":"1942","journal-title":"Doklady Akademii Nauk"},{"key":"ref3","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal Transport: Old and New","volume":"338","author":"Villani","year":"2009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/417260a"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32160-3_1"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2695801"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1090\/psapm\/076\/05"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2018.01.009"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"ref11","article-title":"Transport optimal pour l\u2019apprentissage statistique","author":"Flamary","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20828-2"},{"key":"ref13","volume-title":"M\u00e9moire Sur le Calcul Int\u00e9gral des \u00c9quations aux Diff\u00c9rences partielles","author":"Monge","year":"1784"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160440402"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1006\/aima.1997.1634"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/100805741"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/1428011"},{"key":"ref19","first-page":"229","article-title":"Information-type measures of difference of probability distributions and indirect observation","volume":"2","author":"Csisz\u00e1r","year":"1967","journal-title":"Studia Scientiarum Mathematicarum Hungarica"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1214\/12-EJS722"},{"key":"ref21","first-page":"1637","article-title":"A kernel approach to comparing distributions","volume-title":"Proc. Nat. Conf. Artif. Intell.","author":"Gretton"},{"issue":"78","key":"ref22","first-page":"1","article-title":"Pot: Python optimal transport","volume":"22","author":"Flamary","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref23","article-title":"Optimal transport tools (OTT): A JAX toolbox for all things Wasserstein","author":"Cuturi","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-68874-4_4"},{"key":"ref25","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref26","first-page":"1608","article-title":"Learning generative models with sinkhorn divergences","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Genevay"},{"key":"ref27","first-page":"5864","article-title":"Differential properties of sinkhorn approximation for learning with Wasserstein distance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Luise"},{"key":"ref28","first-page":"1574","article-title":"Sample complexity of sinkhorn divergences","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Genevay"},{"key":"ref29","first-page":"435","article-title":"Wasserstein barycenter and its application to texture mixing","volume-title":"Proc. Int. Conf. Scale Space Variational Methods Comput. Vis.","author":"Rabin"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0506-3"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2509419"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01090"},{"key":"ref33","first-page":"261","article-title":"Generalized sliced Wasserstein distances","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolouri"},{"key":"ref34","first-page":"9144","article-title":"Distributional reinforcement learning via moment matching","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Nguyen"},{"key":"ref35","first-page":"5072","article-title":"Subspace robust Wasserstein distances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Paty"},{"key":"ref36","first-page":"9383","article-title":"Projection robust Wasserstein distance and Riemannian optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref37","first-page":"4446","article-title":"A Riemannian block coordinate descent method for computing the projection robust Wasserstein distance","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/130929886"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2615921"},{"key":"ref40","first-page":"1771","article-title":"Structured optimal transport","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Alvarez-Melis"},{"key":"ref41","volume-title":"Mathematical Programming\u2013The State of the Art","author":"Lov\u00e1sz","year":"1983"},{"key":"ref42","first-page":"2454","article-title":"Statistical optimal transport via factored couplings","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Forrow"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(93)90224-C"},{"key":"ref44","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref45","article-title":"Large scale optimal transport and mapping estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Seguy"},{"key":"ref46","first-page":"6672","article-title":"Optimal transport mapping via input convex neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Makkuva"},{"key":"ref47","article-title":"Neural optimal transport","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Korotin"},{"key":"ref48","first-page":"146","article-title":"Input convex neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amos"},{"key":"ref49","first-page":"3711","article-title":"Wasserstein training of restricted Boltzmann machines","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Montavon"},{"key":"ref50","first-page":"1","article-title":"Optimal transport: Fast probabilistic approximation with exact solvers","volume":"20","author":"Sommerfeld","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_28"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz003"},{"key":"ref53","first-page":"2131","article-title":"Learning with minibatch Wasserstein: Asymptotic and gradient properties","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Fatras"},{"key":"ref54","first-page":"3186","article-title":"Unbalanced minibatch optimal transport; applications to domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fatras"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s00222-017-0759-8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1090\/mcom\/3303"},{"key":"ref57","first-page":"2903","article-title":"Partial optimal tranport with applications on positive-unlabeled learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chapel"},{"key":"ref58","first-page":"16656","article-title":"Improving mini-batch optimal transport via partial transportation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-011-9093-5"},{"key":"ref60","first-page":"6275","article-title":"Optimal transport for structured data with application on graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Titouan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2005.09.032"},{"key":"ref62","first-page":"2664","article-title":"Gromov-Wasserstein averaging of Kernel and distance matrices","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peyr\u00e9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925903"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfa.2017.08.015"},{"key":"ref65","first-page":"157","article-title":"Integral functionals, normal integrands and measurable selections","volume-title":"Nonlinear Operators and the Calculus of Variations","author":"Rockafellar","year":"2006"},{"key":"ref66","volume-title":"The Nature of Statistical Learning Theory","author":"Vapnik","year":"2013"},{"key":"ref67","volume-title":"Pattern reczognition and Machine Learning","volume":"4","author":"Bishop","year":"2006"},{"key":"ref68","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref70","first-page":"2053","article-title":"Learning with a Wasserstein loss","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Frogner"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6831"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01258"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3094662"},{"key":"ref74","article-title":"Distributionally robust optimization: A review","author":"Rahimian","year":"2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1287\/educ.2019.0198"},{"issue":"103","key":"ref76","first-page":"1","article-title":"Regularization via mass transportation","volume":"20","author":"Shafieezadeh-Abadeh","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052660"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3616865"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"ref80","first-page":"2357","article-title":"Obtaining fairness using optimal transport theory","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gordaliza"},{"key":"ref81","first-page":"15360","article-title":"Exploiting MMD and sinkhorn divergences for fair and transferable representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Oneto"},{"key":"ref82","first-page":"3633","article-title":"A general approach to fairness with optimal transport.","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Chiappa"},{"key":"ref83","article-title":"GAN and VAE from an optimal transport point of view","author":"Genevay","year":"2017"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2018.10.005"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.spl.2006.02.001"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref87","first-page":"5767","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gulrajani"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33676-9_11"},{"key":"ref90","article-title":"How well do WGANs estimate the Wasserstein metric?","author":"Mallasto","year":"2019"},{"key":"ref91","article-title":"Wasserstein GANs work because they fail (to approximate the Wasserstein distance)","author":"Stanczuk","year":"2021"},{"key":"ref92","first-page":"2681","article-title":"Interpolating between optimal transport and MMD using sinkhorn divergences","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Feydy"},{"key":"ref93","first-page":"433","article-title":"A fast proximal point method for computing exact Wasserstein distance","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Xie"},{"key":"ref94","volume-title":"Network Optimization: Continuous and Discrete Models","volume":"8","author":"Bertsekas","year":"1998"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00361"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00383"},{"key":"ref98","first-page":"250","article-title":"Asymptotic guarantees for learning generative models with the sliced-Wasserstein distance","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nadjahi"},{"key":"ref99","first-page":"20802","article-title":"Statistical and topological properties of sliced probability divergences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nadjahi"},{"key":"ref100","article-title":"Autoencoding variational bayes","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref102","article-title":"Adversarial autoencoders","author":"Makhzani","year":"2015"},{"key":"ref103","article-title":"Wasserstein auto-encoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tolstikhin"},{"key":"ref104","first-page":"733","article-title":"Sinkhorn autoencoders","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Patrini"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref107","article-title":"Neural ordinary differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref108","first-page":"3154","article-title":"How to train your neural ode: The world of Jacobian and kinetic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finlay"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(97)00169-7"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1002\/env.3170050203"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206834"},{"key":"ref112","first-page":"630","article-title":"Fast dictionary learning with a smoothed Wasserstein loss","volume-title":"Proc. Artif. Intell. Statist.","author":"Rolet"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1137\/17M1140431"},{"key":"ref114","first-page":"10564","article-title":"Online graph dictionary learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vincent-Cuaz"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6120"},{"key":"ref116","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref117","first-page":"957","article-title":"From word embeddings to document distances","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kusner"},{"key":"ref118","first-page":"18573","article-title":"OTLDA: A geometry-aware optimal transport approach for topic modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huynh"},{"key":"ref119","first-page":"1601","article-title":"Hierarchical optimal transport for document representation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yurochkin"},{"key":"ref120","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"Bishop","year":"2006"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056481"},{"key":"ref122","first-page":"2492","article-title":"Learning probability measures with respect to optimal transport metrics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Canas"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.aim.2003.07.017"},{"key":"ref124","volume-title":"Foundations of Quantization for Probability Distributions","author":"Graf","year":"2007"},{"key":"ref125","first-page":"685","article-title":"Fast computation of Wasserstein barycenters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cuturi"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-018-9800-z"},{"key":"ref127","first-page":"1955","article-title":"Co-clustering through optimal transport","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Laclau"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.05.005"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref130","volume-title":"Advances in Domain Adaptation Theory","author":"Redko","year":"2019"},{"key":"ref131","first-page":"4197","article-title":"Mapping estimation for discrete optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Perrot"},{"key":"ref132","first-page":"3733","article-title":"Joint distribution optimal transportation for domain adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Courty"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13560-1_76"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11784"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414199"},{"key":"ref137","first-page":"1970","article-title":"Multi-source domain adaptation via weighted joint distributions optimal transport","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Turrisi"},{"key":"ref138","first-page":"17559","article-title":"Co-optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Redko"},{"key":"ref139","first-page":"849","article-title":"Optimal transport for multi-source domain adaptation under target shift","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Redko"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5152-4"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71246-8_45"},{"key":"ref142","first-page":"21428","article-title":"Geometric dataset distances via optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alvarez Melis"},{"key":"ref143","first-page":"219","article-title":"Dataset dynamics via gradient flows in probability space","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Alvarez-Melis"},{"key":"ref144","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.38.8.716"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/BF00938524"},{"key":"ref148","first-page":"368","article-title":"Parametric return density estimation for reinforcement learning","volume-title":"Proc. 26th Conf. Uncertainty Artif. Intell.","author":"Morimura"},{"key":"ref149","first-page":"1707","article-title":"On the sample complexity of reinforcement learning with a generative model","volume-title":"Proc. 29th Int. Cof. Int. Conf. Mach. Learn.","author":"Azar"},{"key":"ref150","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1561\/2200000049"},{"key":"ref153","first-page":"4335","article-title":"Propagating uncertainty in reinforcement learning via Wasserstein barycenters","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Metelli"},{"key":"ref154","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref155","article-title":"Stein variational policy gradient","author":"Liu","year":"2017"},{"key":"ref156","first-page":"5737","article-title":"Policy optimization as Wasserstein gradient flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref157","volume-title":"Gradient Flows: In Metric Spaces and in the Space of Probability Measures","author":"Ambrosio","year":"2008"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/s13373-017-0101-1"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1137\/S0036141096303359"},{"key":"ref160","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177697802"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.3150\/18-BEJ1065"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.3150\/21-bej1433"},{"key":"ref164","first-page":"14593","article-title":"Do neural optimal transport solvers work? a continuous Wasserstein-2 benchmark","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Korotin"},{"key":"ref165","first-page":"17788","article-title":"Revisiting sliced Wasserstein on images: From vectorization to convolution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref166","article-title":"Spherical sliced-Wasserstein","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Bonet"},{"key":"ref167","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-79228-4_1"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/395"},{"key":"ref170","first-page":"12480","article-title":"Don\u2019t generate me: Training differentially private generative models with sinkhorn divergence","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref171","article-title":"Federated Wasserstein distance","author":"Rakotomamonjy","year":"2023"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447236"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230459"},{"key":"ref174","article-title":"Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis","author":"Cheng","year":"2019"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.566"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1924-6"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10835210\/10740308.pdf?arnumber=10740308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T06:03:59Z","timestamp":1736489039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":176,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3489030","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}