{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:09:18Z","timestamp":1778630958725,"version":"3.51.4"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12125103"],"award-info":[{"award-number":["12125103"]}],"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":["12371441"],"award-info":[{"award-number":["12371441"]}],"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":["11871474"],"award-info":[{"award-number":["11871474"]}],"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":["12071362"],"award-info":[{"award-number":["12071362"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFA0714200"],"award-info":[{"award-number":["2020YFA0714200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003819","name":"Natural Science Foundation of Hubei Province","doi-asserted-by":"publisher","award":["2019CFA007"],"award-info":[{"award-number":["2019CFA007"]}],"id":[{"id":"10.13039\/501100003819","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1016\/j.ins.2024.121166","type":"journal-article","created":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T13:51:37Z","timestamp":1720619497000},"page":"121166","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["An error analysis for deep binary classification with sigmoid loss"],"prefix":"10.1016","volume":"681","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0006-3398-9857","authenticated-orcid":false,"given":"Changshi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuling","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-0402-4056","authenticated-orcid":false,"given":"Jerry Zhijian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.ins.2024.121166_br0010","series-title":"Proceedings of the 25th International Conference on Machine Learning","first-page":"608","article-title":"Random classification noise defeats all convex potential boosters","author":"Long","year":"2008"},{"issue":"522","key":"10.1016\/j.ins.2024.121166_br0020","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1080\/01621459.2016.1273116","article-title":"Boosting in the presence of outliers: adaptive classification with nonconvex loss functions","volume":"113","author":"Li","year":"2018","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.ins.2024.121166_br0030","unstructured":"H. Masnadi-Shirazi, N. Vasconcelos, On the design of loss functions for classification: theory, robustness to outliers, and savageboost, Advances in Neural Information Processing Systems 21."},{"issue":"1","key":"10.1016\/j.ins.2024.121166_br0040","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1109\/TCYB.2019.2953337","article-title":"Laplacian Welsch regularization for robust semisupervised learning","volume":"52","author":"Ke","year":"2020","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.ins.2024.121166_br0050","series-title":"Embedded Systems and Artificial Intelligence: Proceedings of ESAI 2019","first-page":"359","article-title":"Robust loss function for deep learning regression with outliers","author":"Sadouk","year":"2020"},{"key":"10.1016\/j.ins.2024.121166_br0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4331","article-title":"A general and adaptive robust loss function","author":"Barron","year":"2019"},{"key":"10.1016\/j.ins.2024.121166_br0070","unstructured":"S. Fu, X. Wang, J. Tang, S. Lan, Y. Tian, Generalized robust loss functions for machine learning, Neural Netw."},{"issue":"479","key":"10.1016\/j.ins.2024.121166_br0080","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1198\/016214507000000617","article-title":"Robust truncated hinge loss support vector machines","volume":"102","author":"Wu","year":"2007","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.ins.2024.121166_br0090","doi-asserted-by":"crossref","first-page":"6200","DOI":"10.1109\/TNNLS.2021.3134675","article-title":"Generalization analysis of cnns for classification on spheres","volume":"34","author":"Feng","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.ins.2024.121166_br0100","series-title":"Deep Convolutional Neural Networks","first-page":"1","author":"Zhou","year":"2021"},{"key":"10.1016\/j.ins.2024.121166_br0110","first-page":"2876","article-title":"Approximation with cnns in Sobolev space: with applications to classification","volume":"35","author":"Shen","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.ins.2024.121166_br0120","doi-asserted-by":"crossref","first-page":"181","DOI":"10.3982\/ECTA16901","article-title":"Deep neural networks for estimation and inference","volume":"89","author":"Farrell","year":"2021","journal-title":"Econometrica"},{"key":"10.1016\/j.ins.2024.121166_br0130","series-title":"International Conference on Machine Learning, PMLR","first-page":"6770","article-title":"Besov function approximation and binary classification on low-dimensional manifolds using convolutional residual networks","author":"Liu","year":"2021"},{"key":"10.1016\/j.ins.2024.121166_br0140","author":"Zhang"},{"key":"10.1016\/j.ins.2024.121166_br0150","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.neunet.2021.12.016","article-title":"Fully-corrective gradient boosting with squared hinge: fast learning rates and early stopping","volume":"147","author":"Zeng","year":"2020","journal-title":"Neural Netw."},{"key":"10.1016\/j.ins.2024.121166_br0160","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.neunet.2021.02.012","article-title":"Fast convergence rates of deep neural networks for classification","volume":"138","author":"Kim","year":"2021","journal-title":"Neural Netw."},{"key":"10.1016\/j.ins.2024.121166_br0170","author":"Ohn"},{"key":"10.1016\/j.ins.2024.121166_br0180","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1214\/009053606000001217","article-title":"Fast learning rates for plug-in classifiers","volume":"35","author":"Audibert","year":"2007","journal-title":"Ann. Stat."},{"key":"10.1016\/j.ins.2024.121166_br0190","series-title":"Support Vector Machines","author":"Steinwart","year":"2008"},{"issue":"473","key":"10.1016\/j.ins.2024.121166_br0200","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1198\/016214505000000907","article-title":"Convexity, classification, and risk bounds","volume":"101","author":"Bartlett","year":"2006","journal-title":"J. Am. Stat. Assoc."},{"issue":"1","key":"10.1016\/j.ins.2024.121166_br0210","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1214\/aos\/1079120130","article-title":"Statistical behavior and consistency of classification methods based on convex risk minimization","volume":"32","author":"Zhang","year":"2004","journal-title":"Ann. Stat."},{"issue":"1","key":"10.1016\/j.ins.2024.121166_br0220","first-page":"7018","article-title":"Adaptive approximation and generalization of deep neural network with intrinsic dimensionality","volume":"21","author":"Nakada","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"10.1016\/j.ins.2024.121166_br0230","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1214\/18-AOS1747","article-title":"On deep learning as a remedy for the curse of dimensionality in nonparametric regression","volume":"47","author":"Bauer","year":"2019","journal-title":"Ann. Stat."},{"issue":"4","key":"10.1016\/j.ins.2024.121166_br0240","doi-asserted-by":"crossref","first-page":"2231","DOI":"10.1214\/20-AOS2034","article-title":"On the rate of convergence of fully connected deep neural network regression estimates","volume":"49","author":"Kohler","year":"2021","journal-title":"Ann. Stat."},{"key":"10.1016\/j.ins.2024.121166_br0250","doi-asserted-by":"crossref","unstructured":"A. Van der Vaart, J.A. Wellner, Weak Convergence and Empirical Processes. With Applications to Statistics, 1996.","DOI":"10.1007\/978-1-4757-2545-2"},{"key":"10.1016\/j.ins.2024.121166_br0260","series-title":"Empirical Processes in M-Estimation, vol. 6","author":"Geer","year":"2000"},{"key":"10.1016\/j.ins.2024.121166_br0270","series-title":"Mathematical Foundations of Infinite-Dimensional Statistical Models","author":"Gin\u00e9","year":"2021"},{"key":"10.1016\/j.ins.2024.121166_br0280","author":"Bartlett"},{"key":"10.1016\/j.ins.2024.121166_br0290","author":"Koltchinskii"},{"key":"10.1016\/j.ins.2024.121166_br0300","author":"Kingma"},{"key":"10.1016\/j.ins.2024.121166_br0310","series-title":"2019 IEEE International Conference on Big Data and Smart Computing (BigComp)","first-page":"1","article-title":"Combining outlier detection and reconstruction error minimization for label noise reduction","author":"Zhang","year":"2019"},{"key":"10.1016\/j.ins.2024.121166_br0320","series-title":"Noise Versus Outliers","first-page":"163","author":"Salgado","year":"2016"},{"issue":"116","key":"10.1016\/j.ins.2024.121166_br0330","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."},{"key":"10.1016\/j.ins.2024.121166_br0340","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s00365-006-0662-3","article-title":"How to compare different loss functions and their risks","volume":"26","author":"Steinwart","year":"2007","journal-title":"Constr. Approx."},{"key":"10.1016\/j.ins.2024.121166_br0350","author":"Chui"},{"key":"10.1016\/j.ins.2024.121166_br0360","series-title":"Neural Network Learning: Theoretical Foundations, vol. 9","author":"Anthony","year":"1999"},{"issue":"1","key":"10.1016\/j.ins.2024.121166_br0370","first-page":"2285","article-title":"Nearly-tight vc-dimension and pseudodimension bounds for piecewise linear neural networks","volume":"20","author":"Bartlett","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.ins.2024.121166_br0380","author":"Srebro"},{"key":"10.1016\/j.ins.2024.121166_br0390","author":"Liu"},{"issue":"473","key":"10.1016\/j.ins.2024.121166_br0400","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1198\/016214505000000907","article-title":"Convexity, classification, and risk bounds","volume":"101","author":"Bartlett","year":"2006","journal-title":"J. Am. Stat. Assoc."},{"key":"10.1016\/j.ins.2024.121166_br0410","series-title":"Advances in Neural Information Processing Systems","first-page":"41343","article-title":"The adversarial consistency of surrogate risks for binary classification","author":"Frank","year":"2023"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025524010806?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/api.elsevier.com\/content\/article\/PII:S0020025524010806?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T23:15:25Z","timestamp":1778627725000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025524010806"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":41,"alternative-id":["S0020025524010806"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2024.121166","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An error analysis for deep binary classification with sigmoid loss","name":"articletitle","label":"Article Title"},{"value":"Information Sciences","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1016\/j.ins.2024.121166","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"121166"}}