{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T23:41:29Z","timestamp":1773877289459,"version":"3.50.1"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004733","name":"Universidade de Macau","doi-asserted-by":"publisher","award":["MYRG2020-00039-FS"],"award-info":[{"award-number":["MYRG2020-00039-FS"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002358","name":"Beihang University","doi-asserted-by":"publisher","award":["KG16329201"],"award-info":[{"award-number":["KG16329201"]}],"id":[{"id":"10.13039\/501100002358","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515110469"],"award-info":[{"award-number":["2023A1515110469"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12071499"],"award-info":[{"award-number":["12071499"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12101630"],"award-info":[{"award-number":["12101630"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Multivariate Analysis"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.jmva.2025.105571","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T16:37:25Z","timestamp":1764347845000},"page":"105571","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Statistical guarantees for distribution estimation of contaminated data via DNN-based MoM-GANs"],"prefix":"10.1016","volume":"212","author":[{"given":"Fang","family":"Xie","sequence":"first","affiliation":[]},{"given":"Lihu","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Qiuran","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Huiming","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jmva.2025.105571_b1","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jmva.2025.105571_b2","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"136","article-title":"When OT meets MoM: Robust estimation of Wasserstein distance","author":"Staerman","year":"2021"},{"issue":"116","key":"10.1016\/j.jmva.2025.105571_b3","first-page":"1","article-title":"An error analysis of generative adversarial networks for learning distributions","volume":"23","author":"Huang","year":"2022","journal-title":"J. Mach. Learn. Res."},{"issue":"7","key":"10.1016\/j.jmva.2025.105571_b4","first-page":"52","article-title":"On a space of completely additive functions","volume":"13","author":"Kantorovich","year":"1958","journal-title":"Vestnik Leningr. Univ."},{"issue":"228","key":"10.1016\/j.jmva.2025.105571_b5","first-page":"1","article-title":"How well generative adversarial networks learn distributions","volume":"22","author":"Liang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"issue":"11","key":"10.1016\/j.jmva.2025.105571_b6","doi-asserted-by":"crossref","first-page":"7155","DOI":"10.1109\/TIT.2020.2983698","article-title":"Deconstructing generative adversarial networks","volume":"66","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Inform. Theory"},{"issue":"1","key":"10.1016\/j.jmva.2025.105571_b7","first-page":"5287","article-title":"Some theoretical insights into Wasserstein GANs","volume":"22","author":"Biau","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jmva.2025.105571_b8","series-title":"Algorithmic Learning Theory","first-page":"1051","article-title":"Statistical guarantees for generative models without domination","author":"Schreuder","year":"2021"},{"key":"10.1016\/j.jmva.2025.105571_b9","series-title":"Generalization properties of optimal transport GANs with latent distribution learning","author":"Luise","year":"2020"},{"key":"10.1016\/j.jmva.2025.105571_b10","series-title":"International Conference on Machine Learning","first-page":"224","article-title":"Generalization and equilibrium in generative adversarial nets (gans)","author":"Arora","year":"2017"},{"issue":"1","key":"10.1016\/j.jmva.2025.105571_b11","first-page":"312","article-title":"Robust W-GAN-based estimation under Wasserstein contamination","volume":"12","author":"Liu","year":"2023","journal-title":"Inf. Inference: A J. IMA"},{"key":"10.1016\/j.jmva.2025.105571_b12","unstructured":"G. Chao, Y. Yuan, Z. Weizhi, Robust estimation via generative adversarial networks, in: International Conference on Learning Representations, 2018, pp. 1\u201327."},{"key":"10.1016\/j.jmva.2025.105571_b13","first-page":"1","article-title":"A direct approach to robust deep learning using adversarial networks","author":"Wang","year":"2019","journal-title":"Int. Conf. Learn. Represent."},{"issue":"4","key":"10.1016\/j.jmva.2025.105571_b14","doi-asserted-by":"crossref","DOI":"10.3390\/math13040665","article-title":"Selective reviews of Bandit problems in AI via a statistical view","volume":"13","author":"Zhou","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.jmva.2025.105571_b15","first-page":"1","article-title":"DeepMoM: Robust deep learning with median-of-means","author":"Huang","year":"2022","journal-title":"J. Comput. Graph. Statist."},{"issue":"2","key":"10.1016\/j.jmva.2025.105571_b16","doi-asserted-by":"crossref","first-page":"906","DOI":"10.1214\/19-AOS1828","article-title":"Robust machine learning by median-of-means: theory and practice","volume":"48","author":"Lecu\u00e9","year":"2020","journal-title":"Ann. Statist."},{"issue":"3","key":"10.1016\/j.jmva.2025.105571_b17","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1007\/s00440-019-00931-3","article-title":"Robust statistical learning with Lipschitz and convex loss functions","volume":"176","author":"Chinot","year":"2020","journal-title":"Probab. Theory Related Fields"},{"key":"10.1016\/j.jmva.2025.105571_b18","series-title":"Risk bounds for robust deep learning","author":"Lederer","year":"2020"},{"issue":"92","key":"10.1016\/j.jmva.2025.105571_b19","first-page":"1","article-title":"Non-asymptotic guarantees for robust statistical learning under infinite variance assumption","volume":"24","author":"Xu","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jmva.2025.105571_b20","series-title":"Learning to simulate from heavy-tailed distribution via diffusion model","author":"Liu","year":"2024"},{"key":"10.1016\/j.jmva.2025.105571_b21","unstructured":"K. Pandey, J. Pathak, Y. Xu, S. Mandt, M. Pritchard, A. Vahdat, M. Mardani, Heavy-Tailed Diffusion Models, in: 13th International Conference on Learning Representations, 2025, pp. 1\u201355."},{"key":"10.1016\/j.jmva.2025.105571_b22","series-title":"Heavy-tailed denoising score matching","author":"Deasy","year":"2021"},{"key":"10.1016\/j.jmva.2025.105571_b23","article-title":"Score-based generative models with L\u00e9vy processes","volume":"36","author":"Yoon","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jmva.2025.105571_b24","article-title":"Ambient diffusion: Learning clean distributions from corrupted data","volume":"36","author":"Daras","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jmva.2025.105571_b25","article-title":"GSURE-based diffusion model training with corrupted data","author":"Kawar","year":"2025","journal-title":"Trans. Mach. Learn. Res."},{"issue":"2","key":"10.1016\/j.jmva.2025.105571_b26","doi-asserted-by":"crossref","first-page":"429","DOI":"10.2307\/1428011","article-title":"Integral probability metrics and their generating classes of functions","volume":"29","author":"M\u00fcller","year":"1997","journal-title":"Adv. in Appl. Probab."},{"key":"10.1016\/j.jmva.2025.105571_b27","series-title":"International Conference on Machine Learning","first-page":"214","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"10.1016\/j.jmva.2025.105571_b28","series-title":"International Conference on Machine Learning","first-page":"1718","article-title":"Generative moment matching networks","author":"Li","year":"2015"},{"key":"10.1016\/j.jmva.2025.105571_b29","series-title":"Problem Complexity and Method Efficiency in Optimization","author":"Nemirovskij","year":"1983"},{"key":"10.1016\/j.jmva.2025.105571_b30","series-title":"Lecture notes: Selected topics on robust statistical learning theory","author":"Lerasle","year":"2019"},{"issue":"2","key":"10.1016\/j.jmva.2025.105571_b31","doi-asserted-by":"crossref","first-page":"3752","DOI":"10.1214\/16-EJS1216","article-title":"A general decision theory for Huber\u2019s \u03f5-contamination model","volume":"10","author":"Chen","year":"2016","journal-title":"Electron. J. Stat."},{"key":"10.1016\/j.jmva.2025.105571_b32","series-title":"International Conference on Machine Learning","first-page":"5937","article-title":"Generalization bounds in the presence of outliers: a median-of-means study","author":"Laforgue","year":"2021"},{"key":"10.1016\/j.jmva.2025.105571_b33","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.neunet.2021.10.012","article-title":"On the capacity of deep generative networks for approximating distributions","volume":"145","author":"Yang","year":"2022","journal-title":"Neural Netw."},{"issue":"2","key":"10.1016\/j.jmva.2025.105571_b34","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1214\/aop\/1019160263","article-title":"About the constants in Talagrand\u2019s concentration inequalities for empirical processes","volume":"28","author":"Massart","year":"2000","journal-title":"Ann. Probab."},{"key":"10.1016\/j.jmva.2025.105571_b35","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.neunet.2021.04.034","article-title":"Statistical guarantees for regularized neural networks","volume":"142","author":"Taheri","year":"2021","journal-title":"Neural Netw."},{"key":"10.1016\/j.jmva.2025.105571_b36","first-page":"26","article-title":"Divide the gradient by a running average of its recent magnitude. coursera: Neural networks for machine learning","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA: Neural Netw. Mach. Learn."},{"key":"10.1016\/j.jmva.2025.105571_b37","series-title":"MNIST Handwritten Digit Database","author":"LeCun","year":"2010"},{"key":"10.1016\/j.jmva.2025.105571_b38","series-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.jmva.2025.105571_b39","unstructured":"A. Radford, L. Metz, S. Chintala, Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, in: 4th International Conference on Learning Representations, 2016, pp. 1\u201316."},{"issue":"3","key":"10.1016\/j.jmva.2025.105571_b40","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1016\/0047-259X(82)90077-X","article-title":"The Fr\u00e9chet distance between multivariate normal distributions","volume":"12","author":"Dowson","year":"1982","journal-title":"J. Multivariate Anal."},{"key":"10.1016\/j.jmva.2025.105571_b41","series-title":"Weak Convergence and Empirical Processes: With Applications to Statistics","author":"van der Vaart","year":"1996"},{"issue":"1","key":"10.1016\/j.jmva.2025.105571_b42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4208\/cmr.2020-0041","article-title":"Concentration inequalities for statistical inference","volume":"37","author":"Zhang","year":"2021","journal-title":"Commun. Math. Res."},{"key":"10.1016\/j.jmva.2025.105571_b43","series-title":"Learning Theory From First Principles","author":"Bach","year":"2024"},{"key":"10.1016\/j.jmva.2025.105571_b44","volume":"vol. 23","author":"Ledoux","year":"1991"}],"container-title":["Journal of Multivariate Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0047259X25001666?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0047259X25001666?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T16:39:19Z","timestamp":1773851959000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0047259X25001666"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":44,"alternative-id":["S0047259X25001666"],"URL":"https:\/\/doi.org\/10.1016\/j.jmva.2025.105571","relation":{},"ISSN":["0047-259X"],"issn-type":[{"value":"0047-259X","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Statistical guarantees for distribution estimation of contaminated data via DNN-based MoM-GANs","name":"articletitle","label":"Article Title"},{"value":"Journal of Multivariate Analysis","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jmva.2025.105571","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"105571"}}