{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T22:15:36Z","timestamp":1766182536071,"version":"3.41.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministry of Economic Development of the Russian Federation","award":["25-139-66879-1-0003"],"award-info":[{"award-number":["25-139-66879-1-0003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3578926","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T17:45:54Z","timestamp":1749663954000},"page":"102390-102406","source":"Crossref","is-referenced-by-count":3,"title":["An Approach to Finding a Robust Deep Learning Model"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7872-6819","authenticated-orcid":false,"given":"Alexey","family":"Boldyrev","sequence":"first","affiliation":[{"name":"Laboratory of Methods for Big Data Analysis, HSE University, Moscow, Russia"}]},{"given":"Fedor","family":"Ratnikov","sequence":"additional","affiliation":[{"name":"Laboratory of Methods for Big Data Analysis, HSE University, Moscow, Russia"}]},{"given":"Andrey","family":"Shevelev","sequence":"additional","affiliation":[{"name":"Laboratory of Methods for Big Data Analysis, HSE University, Moscow, Russia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02134016"},{"key":"ref2","article-title":"Approximating continuous functions by ReLU nets of minimal width","author":"Hanin","year":"2017","journal-title":"arXiv:1710.11278"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1142\/S1469026818500086"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3447582"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3253818"},{"key":"ref6","first-page":"7105","article-title":"NAS-Bench-101: Towards reproducible neural architecture search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ying"},{"key":"ref7","article-title":"NAS-Bench-201: Extending the scope of reproducible neural architecture search","author":"Dong","year":"2020","journal-title":"arXiv:2001.00326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3169897"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.revip.2023.100085"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_594"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2006.03.004"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-024-01171-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref17","first-page":"512","article-title":"Robust training and initialization of deep neural networks: An adaptive basis viewpoint","volume-title":"Proc. Math. Sci. Mach. Learn. Conf.","author":"Cyr"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","first-page":"36094","article-title":"Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref20","article-title":"Double descent demystified: Identifying, interpreting & ablating the sources of a deep learning puzzle","author":"Schaeffer","year":"2023","journal-title":"arXiv:2303.14151"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2107151119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9a90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0068"},{"key":"ref25","first-page":"5637","article-title":"WILDS: A benchmark of in-the-wild distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Koh"},{"key":"ref26","first-page":"11539","article-title":"Improving robustness against common corruptions by covariate shift adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schneider"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/591"},{"key":"ref28","article-title":"Opportunities and challenges in deep learning adversarial robustness: A survey","author":"Silva","year":"2020","journal-title":"arXiv:2007.00753"},{"key":"ref29","article-title":"Tree-structured Parzen estimator: Understanding its algorithm components and their roles for better empirical performance","author":"Watanabe","year":"2023","journal-title":"arXiv:2304.11127"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0168-9002(03)01368-8"},{"article-title":"Design and construction of electromagnetic calorimeter for LHCB experiment","year":"2000","author":"Barsuk","key":"ref31"},{"issue":"8","key":"ref32","article-title":"The LHCb detector at the LHC","volume":"3","author":"Alves","year":"2008","journal-title":"J. Instrum."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/15\/09\/C09030"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0168-9002(97)00048-X"},{"key":"ref35","article-title":"Uproot","author":"Pivarski","year":"2024","journal-title":"Zenodo"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/0168-9002(92)90858-2"},{"article-title":"S-shape correction using a neural network","year":"1998","author":"Schwindling","key":"ref38"},{"article-title":"Position resolution of an atlas electromagnetic calorimeter module","year":"2003","author":"Sacco","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.75.1243"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05441-7"},{"key":"ref42","first-page":"2672","article-title":"On the impact of the activation function on deep neural networks training","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hayou"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1710.05941"},{"key":"ref44","article-title":"Fast and accurate deep network learning by exponential linear units (ELUs)","author":"Clevert","year":"2015","journal-title":"arXiv:1511.07289"},{"key":"ref45","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016","journal-title":"arXiv:1606.08415"},{"key":"ref46","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"ref48","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hardt"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"issue":"61","key":"ref50","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"Duchi","year":"2011","journal-title":"J. Mach. Learn. Res."},{"volume-title":"Neural Networks For Machine Learning Lecture Notes [PowerPoint slides]","year":"2012","author":"Hinton","key":"ref51"},{"key":"ref52","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler","year":"2012","journal-title":"arXiv:1212.5701"},{"issue":"3","key":"ref53","first-page":"543","article-title":"A method of solving a convex programming problem with convergence rate o (1\/k** 2)","volume":"269","author":"Nesterov","year":"1983","journal-title":"Doklady Akademii Nauk SSSR"},{"key":"ref54","first-page":"2013","article-title":"Incorporating nesterov momentum into adam","volume-title":"Proc. Workshop ICLR","author":"Dozat"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1740\/1\/012050"},{"volume-title":"Torchinfo","year":"2020","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11030460.pdf?arnumber=11030460","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:41:09Z","timestamp":1750268469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11030460\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3578926","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}