{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:22:59Z","timestamp":1786123379777,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045577","type":"print"},{"value":"9783032045584","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T00:00:00Z","timestamp":1757635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04558-4_9","type":"book-chapter","created":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:16:05Z","timestamp":1757589365000},"page":"105-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Parallelizing Sharpness-Aware Minimization: A Semi-asynchronous, Small-Batch Approach"],"prefix":"10.1007","author":[{"given":"Weimin","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,12]]},"reference":[{"key":"9_CR1","unstructured":"Yang, A., et al.: Qwen2. 5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"9_CR2","unstructured":"Wang, T., et al.: What language model architecture and pretraining objective works best for zero-shot generalization? In: International Conference on Machine Learning, pp. 22964\u201322984. PMLR (2022)"},{"key":"9_CR3","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)"},{"key":"9_CR4","unstructured":"Foret, P., Kleiner, A., Mobahi, H., Neyshabur, B.: Sharpness-aware minimization for efficiently improving generalization. In: International Conference on Learning Representations (2020)"},{"key":"9_CR5","unstructured":"Keskar, N.S., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On large-batch training for deep learning: generalization gap and sharp minima. In: International Conference on Learning Representations (2016)"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Y., Mai, S., Chen, X., Hsieh, C.J., You, Y.: Towards efficient and scalable sharpness-aware minimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12360\u201312370 (2022)","DOI":"10.1109\/CVPR52688.2022.01204"},{"key":"9_CR7","unstructured":"Kwon, J., Kim, J., Park, H., Choi, I.K.: Asam: adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks. In: International Conference on Machine Learning, pp. 5905\u20135914. PMLR (2021)"},{"key":"9_CR8","unstructured":"Jiang, W., Yang, H., Zhang, Y., Kwok, J.: An adaptive policy to employ sharpness-aware minimization. arXiv preprint arXiv:2304.14647 (2023)"},{"key":"9_CR9","unstructured":"Du, J., et al.: Efficient sharpness-aware minimization for improved training of neural networks. arXiv preprint arXiv:2110.03141 (2021)"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"30950","DOI":"10.52202\/068431-2244","volume":"35","author":"P Mi","year":"2022","unstructured":"Mi, P., et al.: Make sharpness-aware minimization stronger: a sparsified perturbation approach. Adv. Neural. Inf. Process. Syst. 35, 30950\u201330962 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR11","unstructured":"Zheng, S., et al.: Asynchronous stochastic gradient descent with delay compensation. In: International Conference on Machine Learning, pp. 4120\u20134129. PMLR (2017)"},{"key":"9_CR12","unstructured":"Kaur, S., Cohen, J., Lipton, Z.C.: On the maximum hessian eigenvalue and generalization. In: Proceedings on, pp. 51\u201365. PMLR (2023)"},{"key":"9_CR13","unstructured":"Neyshabur, B., Bhojanapalli, S., McAllester, D., Srebro, N.: Exploring generalization in deep learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"9_CR14","unstructured":"Jia, Z., Su, H.: Information-theoretic local minima characterization and regularization. In: International Conference on Machine Learning, pp. 4773\u20134783. PMLR (2020)"},{"key":"9_CR15","first-page":"18420","volume":"34","author":"H Petzka","year":"2021","unstructured":"Petzka, H., Kamp, M., Adilova, L., Sminchisescu, C., Boley, M.: Relative flatness and generalization. Adv. Neural. Inf. Process. Syst. 34, 18420\u201318432 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR16","unstructured":"Cohen, J., Kaur, S., Li, Y., Kolter, J.Z., Talwalkar, A.: Gradient descent on neural networks typically occurs at the edge of stability. In: International Conference on Learning Representations (2021)"},{"key":"9_CR17","unstructured":"Lewkowycz, A., Bahri, Y., Dyer, E., Sohl-Dickstein, J., Gur-Ari, G.: The large learning rate phase of deep learning: the catapult mechanism. arXiv preprint arXiv:2003.02218 (2020)"},{"key":"9_CR18","unstructured":"Jastrz\u0119bski, S., et al.: Three factors influencing minima in SGD. arXiv preprint arXiv:1711.04623 (2017)"},{"key":"9_CR19","unstructured":"Smith, S.L., Le, Q.V.: A Bayesian perspective on generalization and stochastic gradient descent. In: International Conference on Learning Representations (2018)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Xie, W., Pethick, T., Cevher, V.: Sampa: sharpness-aware minimization parallelized. In: 38th Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-1625"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Mueller, M., Vlaar, T., Rolnick, D., Hein, M.: Normalization layers are all that sharpness-aware minimization needs. In: Advances in Neural Information Processing Systems, vol. 36 (2024)","DOI":"10.52202\/075280-3031"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Du, J., Zhou, D., Feng, J., Tan, V., Zhou, J.T.: Sharpness-aware training for free. In: Advances in Neural Information Processing Systems (2022)","DOI":"10.52202\/068431-1703"},{"key":"9_CR23","doi-asserted-by":"publisher","first-page":"70861","DOI":"10.52202\/075280-3104","volume":"36","author":"B Li","year":"2023","unstructured":"Li, B., Giannakis, G.: Enhancing sharpness-aware optimization through variance suppression. Adv. Neural. Inf. Process. Syst. 36, 70861\u201370879 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR24","unstructured":"Kong, L., Lin, T., Koloskova, A., Jaggi, M., Stich, S.: Consensus control for decentralized deep learning. In: International Conference on Machine Learning, pp. 5686\u20135696. PMLR (2021)"},{"key":"9_CR25","unstructured":"Zhang, W., Liu, M., Feng, Y., Cui, X., Kingsbury, B., Tu, Y.: Loss landscape dependent self-adjusting learning rates in decentralized stochastic gradient descent. arXiv preprint arXiv:2112.01433 (2021)"},{"key":"9_CR26","unstructured":"Zhu, T., He, F., Chen, K., Song, M., Tao, D.: Decentralized SGD and average-direction SAM are asymptotically equivalent. In: International Conference on Machine Learning, pp. 43005\u201343036. PMLR (2023)"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.H., Friedman, J.H.: The Elements of Statistical Learning: Data Mining, Inference, and Prediction, vol. 2. Springer (2009)","DOI":"10.1007\/978-0-387-84858-7"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T.S.: Neural collaborative filtering. In: Proceedings of the 26th International Conference on World Wide Web, pp. 173\u2013182 (2017)","DOI":"10.1145\/3038912.3052569"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"9_CR30","unstructured":"Wen, K., Ma, T., Li, Z.: How does sharpness-aware minimization minimize sharpness? arXiv preprint arXiv:2211.05729 (2022)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04558-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:23:02Z","timestamp":1786112582000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04558-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,12]]},"ISBN":["9783032045577","9783032045584"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04558-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,12]]},"assertion":[{"value":"12 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}