{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:40:09Z","timestamp":1778085609945,"version":"3.51.4"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890114","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Sharpness-Aware Minimization with Adaptive Regularization for Training Deep Neural Networks"],"prefix":"10.1109","author":[{"given":"Jinping","family":"Zou","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoge","family":"Deng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01505-1"},{"key":"ref2","first-page":"639","article-title":"Towards understanding sharpness-aware minimization","volume-title":"International Conference on Machine Learning","author":"Andriushchenko"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/02331934.2021.1892104"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/16m1080173"},{"key":"ref5","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29","author":"Du"},{"key":"ref6","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Foret"},{"key":"ref7","article-title":"Understanding the role of momentum in stochastic gradient methods","volume":"32","author":"Gitman","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Fantastic generalization measures and where to find them","volume-title":"8th International Conference on Learning Representations, ICLR 2020","author":"Jiang"},{"key":"ref10","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Keskar"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73420-5_11"},{"key":"ref12","first-page":"1895","article-title":"Sub-sampled cubic regularization for non-convex optimization","volume-title":"International Conference on Machine Learning","author":"Kohler"},{"key":"ref13","first-page":"5905","article-title":"Asam: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks","volume-title":"International Conference on Machine Learning","author":"Kwon"},{"key":"ref14","article-title":"Enhancing sharpness-aware optimization through variance suppression","volume-title":"Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems, NeurIPS 2023","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00538"},{"key":"ref16","first-page":"6553","article-title":"A second look at exponential and cosine step sizes: Simplicity, adaptivity, and performance","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01204"},{"key":"ref18","first-page":"30950","article-title":"Make sharpnessaware minimization stronger: A sparsified perturbation approach","volume":"35","author":"Mi","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.10.044"},{"key":"ref20","first-page":"20790","article-title":"Adaptive random walk gradient descent for decentralized optimization","volume-title":"ICML","author":"Sun","year":"2022"},{"key":"ref21","article-title":"Training deep neural networks with adaptive momentum inspired by the quadratic optimization","author":"Sun","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038535"},{"key":"ref23","article-title":"General proximal incremental aggregated gradient algorithms: Better and novel results under general scheme","volume":"32","author":"Sun","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3233\/faia230568"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890114.pdf?arnumber=10890114","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:30Z","timestamp":1774416330000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890114\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890114","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}