{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T21:13:43Z","timestamp":1762982023109,"version":"3.40.3"},"reference-count":98,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFA1014202"],"award-info":[{"award-number":["2024YFA1014202"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12125103","U24A2002","12371441"],"award-info":[{"award-number":["12125103","U24A2002","12371441"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tit.2025.3537594","type":"journal-article","created":{"date-parts":[[2025,1,31]],"date-time":"2025-01-31T18:30:24Z","timestamp":1738348224000},"page":"2955-2981","source":"Crossref","is-referenced-by-count":1,"title":["Semi-Supervised Deep Sobolev Regression: Estimation and Variable Selection by ReQU Neural Network"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5151-7264","authenticated-orcid":false,"given":"Zhao","family":"Ding","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0815-6281","authenticated-orcid":false,"given":"Chenguang","family":"Duan","sequence":"additional","affiliation":[{"name":"School of Mathematics and Statistics, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuling","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the National Center for Applied Mathematics in Hubei, Hubei Key Laboratory of Computational Science, and the School of Mathematics and Statistics, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0402-4056","authenticated-orcid":false,"given":"Jerry Zhijian","family":"Yang","sequence":"additional","affiliation":[{"name":"National Center for Applied Mathematics in Hubei, Wuhan Institute for Math & Al, the School of Mathematics and Statistics, and Hubei Key Laboratory of Computational Science, Wuhan University, Wuhan, Hubei, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/b97848"},{"volume-title":"All of Nonparametric Statistics","year":"2006","author":"Wasserman","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/b13794"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155328"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.165600"},{"key":"ref6","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Rifai"},{"key":"ref7","first-page":"1","article-title":"Gradient descent gan optimization is locally stable","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Nagarajan"},{"key":"ref8","first-page":"1","article-title":"Stabilizing training of generative adversarial networks through regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Roth"},{"key":"ref9","article-title":"Improved training of Wasserstein GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Gulrajani"},{"key":"ref10","first-page":"336","article-title":"Deep generative learning via Euler particle transport","volume-title":"Proc. 2nd Math. Sci. Mach. Learn. Conf.","volume":"145","author":"Gao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2015.84"},{"key":"ref12","first-page":"2266","article-title":"Formal guarantees on the robustness of a classifier against adversarial manipulation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hein"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00928"},{"key":"ref14","first-page":"1","article-title":"Sensitivity and generalization in neural networks: An empirical study","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Novak"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_32"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11504"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-51578-1","volume-title":"Cost and Production Functions","volume":"194","author":"Shephard","year":"1981"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1214\/07-EJS006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/b98886"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1198\/C16214503000000909"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asq056"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5705\/ss.202016.0427"},{"key":"ref23","first-page":"653","article-title":"A regularization approach to nonlinear variable selection","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","volume":"9","author":"Rosasco"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3182\/20120711-3-BE-2027.00364"},{"issue":"52","key":"ref25","first-page":"1665","article-title":"Nonparametric sparsity and regularization","volume":"14","author":"Rosasco","year":"2013","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"ref26","first-page":"331","article-title":"A new variational approach for inverse source problems","volume":"12","author":"Hu","year":"2018","journal-title":"Numer. Math., Theory, Methods Appl."},{"issue":"1","key":"ref27","first-page":"281","article-title":"Derivative estimation with local polynomial fitting","volume":"14","author":"Brabanter","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.2307\/3315976"},{"issue":"266","key":"ref29","first-page":"1","article-title":"On the estimation of derivatives using plug-in kernel ridge regression estimators","volume":"24","author":"Liu","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/74.4.743"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1515\/9781400874668"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref32"},{"key":"ref33","article-title":"Estimation and hypothesis testing of derivatives in smoothing spline ANOVA models","author":"Liu","year":"2023","journal-title":"arXiv:2308.13905"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/18-aos1747"},{"issue":"174","key":"ref35","first-page":"1","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."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1214\/19-aos1875"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/20-AOS2034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3982\/ECTA16901"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3146620"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1214\/23-AOS2266"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970128","volume-title":"Spline Models for Observational Data","author":"Wahba","year":"1990"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/18.998089"},{"issue":"4","key":"ref43","first-page":"475","article-title":"Application of structural risk minimization to multivariate smoothing spline regression estimates","volume":"8","author":"K\u00f6hler","year":"2002","journal-title":"Bernoulli"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176349548"},{"key":"ref45","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-02888-9","volume-title":"Constructive Approximation","volume":"303","author":"DeVore","year":"1993"},{"issue":"1","key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40304-018-0127-z","article-title":"The deep Ritz method: A deep learning-based numerical algorithm for solving variational problems","volume":"6","author":"Weinan","year":"2018","journal-title":"Commun. Math. Statist."},{"issue":"5","key":"ref47","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1017\/S0266466600007143","article-title":"Sobolev estimation of approximate regressions","volume":"12","author":"Florens","year":"1996","journal-title":"Econ. Theory"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1214\/009053606000001127"},{"issue":"2","key":"ref49","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1016\/j.jeconom.2010.03.038","article-title":"Nonparametric least squares estimation in derivative families","volume":"157","author":"Hall","year":"2010","journal-title":"J. Econometrics"},{"key":"ref50","first-page":"453","article-title":"A comparative study of nonparametric derivative estimators","volume-title":"Proc. 22nd Int. Workshop Stat. Model.","author":"Newell"},{"key":"ref51","first-page":"1","article-title":"Derivative estimation in random design","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Liu"},{"issue":"65","key":"ref52","first-page":"1","article-title":"Smoothed nonparametric derivative estimation using weighted difference quotients","volume":"21","author":"Liu","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.2307\/2323093"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-3150-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9892.1996.tb00294.x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-4149(96)00095-6"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s00362-016-0791-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1201\/b15710"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1201\/9781482273144"},{"issue":"1","key":"ref60","first-page":"93","article-title":"On derivative estimation in spline regression","volume":"10","author":"Zhou","year":"2000","journal-title":"Statistica Sinica"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7284-3"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01548-9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref64","first-page":"1","article-title":"The value of unlabeled data for classification problems","volume-title":"Proc. 17th Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref65","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"Belkin","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref66","first-page":"1","article-title":"Statistical analysis of semi-supervised regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Wasserman"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2021.1915320"},{"issue":"2","key":"ref68","doi-asserted-by":"crossref","first-page":"5437","DOI":"10.1214\/22-EJS2070","article-title":"Improved estimators for semi-supervised high-dimensional regression model","volume":"16","author":"Livne","year":"2022","journal-title":"Electron. J. Statist."},{"issue":"546","key":"ref69","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1080\/01621459.2023.2169699","article-title":"A general M-estimation theory in semi-supervised framework","volume":"119","author":"Song","year":"2024","journal-title":"J. Amer. Stat. Assoc."},{"issue":"548","key":"ref70","doi-asserted-by":"crossref","first-page":"2748","DOI":"10.1080\/01621459.2023.2277409","article-title":"Optimal and safe estimation for high-dimensional semi-supervised learning","volume":"119","author":"Deng","year":"2024","journal-title":"J. Amer. Stat. Assoc."},{"key":"ref71","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-75934-0","volume-title":"The Mathematical Theory of Finite Element Methods","author":"Brenner","year":"2008"},{"key":"ref72","volume-title":"Partial Differential Equations","volume":"19","author":"Evans","year":"2010"},{"key":"ref73","first-page":"639","article-title":"Optimal approximation of continuous functions by very deep ReLU networks","volume-title":"Proc. Conf. Learn. Theory","author":"Yarotsky"},{"key":"ref74","first-page":"13005","article-title":"The phase diagram of approximation rates for deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yarotsky"},{"key":"ref75","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.neunet.2019.07.011","article-title":"Nonlinear approximation via compositions","volume":"119","author":"Shen","year":"2019","journal-title":"Neural Netw."},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2020-0149"},{"issue":"5","key":"ref77","doi-asserted-by":"crossref","first-page":"5465","DOI":"10.1137\/20M134695X","article-title":"Deep network approximation for smooth functions","volume":"53","author":"Lu","year":"2021","journal-title":"SIAM J. Math. Anal."},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.08.019"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.4208\/cicp.OA-2019-0168"},{"issue":"2","key":"ref80","doi-asserted-by":"crossref","first-page":"159","DOI":"10.4208\/jms.v53n2.20.03","article-title":"PowerNet: Efficient representations of polynomials and smooth functions by deep neural networks with rectified power units","volume":"53","author":"Bo Li","year":"2020","journal-title":"J. Math. Study"},{"issue":"4","key":"ref81","doi-asserted-by":"crossref","first-page":"1020","DOI":"10.4208\/cicp.OA-2021-0195","article-title":"Convergence rate analysis for deep Ritz method","volume":"31","author":"Duan","year":"2022","journal-title":"Commun. Comput. Phys."},{"key":"ref82","article-title":"Differentiable neural networks with RePU activation: With applications to score estimation and isotonic regression","author":"Shen","year":"2023","journal-title":"arXiv:2305.00608"},{"issue":"116","key":"ref83","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":"ref84","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.acha.2023.03.004","article-title":"Approximation bounds for norm constrained neural networks with applications to regression and GANs","volume":"65","author":"Jiao","year":"2023","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176345969"},{"issue":"5","key":"ref86","doi-asserted-by":"crossref","first-page":"1564","DOI":"10.1214\/aos\/1017939142","article-title":"Information-theoretic determination of minimax rates of convergence","volume":"27","author":"Yang","year":"1999","journal-title":"Ann. Statist."},{"issue":"4","key":"ref87","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1016\/S0893-6080(96)00098-6","article-title":"Optimal linear combinations of neural networks","volume":"10","author":"Hashem","year":"1997","journal-title":"Neural Netw."},{"issue":"5","key":"ref88","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1142\/S0219530519410021","article-title":"Error bounds for approximations with deep ReLU neural networks in Ws,p norms","volume":"18","author":"G\u00fchring","year":"2020","journal-title":"Anal. Appl."},{"volume-title":"Optimization With PDE Constraints","year":"2009","author":"Hinze","key":"ref89"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/112"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511624216"},{"issue":"63","key":"ref93","first-page":"1","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."},{"issue":"4","key":"ref94","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1007\/s00365-001-0024-6","article-title":"Multivariate simultaneous approximation","volume":"18","author":"Bagby","year":"2002","journal-title":"Constructive Approximation"},{"key":"ref95","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611972030","volume-title":"Elliptic Problems in Nonsmooth Domains","author":"Grisvard","year":"2011"},{"key":"ref96","first-page":"1260","article-title":"Learning with square loss: Localization through offset Rademacher complexity","volume-title":"Proc. 28th Conf. Learn. Theory","author":"Liang"},{"volume-title":"Foundations of Machine Learning","year":"2018","author":"Mohri","key":"ref97"},{"key":"ref98","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/18\/10935829\/10858754.pdf?arnumber=10858754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:32:42Z","timestamp":1743132762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":98,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tit.2025.3537594","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"type":"print","value":"0018-9448"},{"type":"electronic","value":"1557-9654"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}