{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T20:15:29Z","timestamp":1780690529748,"version":"3.54.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2024-00338859"],"award-info":[{"award-number":["RS-2024-00338859"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3695934","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T19:36:47Z","timestamp":1779478607000},"page":"82166-82179","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Effect of Multi-Step Ascent in Sharpness-Aware Minimization"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5361-459X","authenticated-orcid":false,"given":"Hoki","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Industrial Security, Chung-Ang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinseong","family":"Park","sequence":"additional","affiliation":[{"name":"Korea Institute for Advanced Study, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7432-4185","authenticated-orcid":false,"given":"Woojin","family":"Lee","sequence":"additional","affiliation":[{"name":"Graduate School of Computer Science and Artificial Intelligence, Dongguk University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5720-8337","authenticated-orcid":false,"given":"Jaewook","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Seoul National University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9150-704X","authenticated-orcid":false,"given":"Yujin","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Ulsan National Institute of Science and Technology, Ulsan, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5947","article-title":"Exploring generalization in deep learning","volume-title":"Proc. Adv. neural Inf. Process. Syst.","author":"Neyshabur"},{"key":"ref2","first-page":"4604","article-title":"Do we need zero training loss after achieving zero training error","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"1","author":"Ishida"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/307400.307435"},{"key":"ref4","first-page":"1019","article-title":"Sharp minima can generalize for deep nets","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dinh"},{"key":"ref5","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Keskar"},{"key":"ref6","article-title":"Fantastic generalization measures and where to find them","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jiang"},{"key":"ref7","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Izmailov"},{"key":"ref8","article-title":"Asymmetric valleys: Beyond sharp and flat local minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"He"},{"key":"ref9","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Foret"},{"key":"ref10","first-page":"2958","article-title":"Adversarial weight perturbation helps robust generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref11","first-page":"1067","article-title":"Gradient descent can take exponential time to escape saddle points","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Du"},{"key":"ref12","first-page":"2698","article-title":"An alternative view: When does SGD escape local minima?","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Kleinberg"},{"key":"ref13","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Madry"},{"key":"ref14","article-title":"Fast is better than free: Revisiting adversarial training","author":"Wong","year":"2020","journal-title":"arXiv:2001.03994"},{"key":"ref15","article-title":"Analyzing loss landscape of deep learning models for better robustness and generalization","author":"Kim","year":"2023"},{"key":"ref16","first-page":"5905","article-title":"ASAM: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kwon"},{"key":"ref17","article-title":"Surrogate gap minimization improves sharpness-aware training","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhuang"},{"key":"ref18","first-page":"24543","article-title":"Random sharpness-aware minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref19","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Du"},{"key":"ref20","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Andriushchenko"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1625"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28431"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3624332"},{"key":"ref24","article-title":"Visualizing the loss landscape of neural nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16989"},{"key":"ref26","volume-title":"The Large Learning Rate Phase of Deep Learning","author":"Lewkowycz","year":"2021"},{"key":"ref27","article-title":"Stability analysis of sharpness-aware minimization","author":"Kim","year":"2023","journal-title":"arXiv:2301.06308"},{"key":"ref28","article-title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017","journal-title":"arXiv:1703.11008"},{"key":"ref29","volume-title":"Learning Multiple Layers of Features From Tiny Images","author":"Krizhevsky","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5244\/c.30.87"},{"key":"ref33","volume-title":"Proceedings of the Twelfth Annual Conference on Computational Learning Theory","author":"Ben-David","year":"1999"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1015957395"},{"key":"ref35","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref36","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv:1608.03983"},{"key":"ref37","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref38","article-title":"Torchattacks: A PyTorch repository for adversarial attacks","author":"Kim","year":"2020","journal-title":"arXiv:2010.01950"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378171"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11534224.pdf?arnumber=11534224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:40:45Z","timestamp":1780688445000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11534224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3695934","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}