{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T23:03:19Z","timestamp":1784329399602,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819233939","type":"print"},{"value":"9789819233946","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:00:00Z","timestamp":1784332800000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3394-6_11","type":"book-chapter","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T22:20:16Z","timestamp":1784326816000},"page":"124-133","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Curvature-Aware Dynamic Weight Prediction Method for AdamW"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9393-4245","authenticated-orcid":false,"given":"Yuqiao","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9041-3244","authenticated-orcid":false,"given":"Lei","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6233-0211","authenticated-orcid":false,"given":"Xingkui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1000-1109","authenticated-orcid":false,"given":"Yongle","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,18]]},"reference":[{"key":"11_CR1","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. https:\/\/arxiv.org\/abs\/1412.6980 (2014)"},{"key":"11_CR2","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. https:\/\/arxiv.org\/abs\/1711.05101 (2017)"},{"key":"11_CR3","unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of Adam and beyond. https:\/\/arxiv.org\/abs\/1904.09237 (2019)"},{"key":"11_CR4","first-page":"9","volume-title":"Neural Networks: Tricks of the Trade","author":"Y LeCun","year":"2002","unstructured":"LeCun, Y., Bottou, L., Orr, G.B., M\u00fcller, K.R.: Efficient backprop. In: Neural Networks: Tricks of the Trade, pp. 9\u201350. Springer (2002)"},{"key":"11_CR5","first-page":"1","volume":"30","author":"AC Wilson","year":"2017","unstructured":"Wilson, A.C., Roelofs, R., Stern, M., Srebro, N., Recht, B.: The marginal value of adaptive gradient methods. Adv. Neural Inf. Process. Syst. 30, 1\u201311 (2017)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"11_CR6","first-page":"543","volume":"269","author":"Y Nesterov","year":"1983","unstructured":"Nesterov, Y.: A method for convex programming with O (1\/k2) convergence. Dokl. Akad. Nauk SSSR. 269, 543 (1983)","journal-title":"Dokl. Akad. Nauk SSSR"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Guan, L.: Weight prediction boosts AdamW convergence. In: PAC-KD, pp. 329\u2013340. Springer (2023)","DOI":"10.1007\/978-3-031-33374-3_26"},{"key":"11_CR8","first-page":"9596","volume":"32","author":"M Zhang","year":"2019","unstructured":"Zhang, M., Lucas, J., Ba, J., Hinton, G.E.: Lookahead optimizer. Adv. Neural Inf. Process. Syst. 32, 9596\u20139608 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"11_CR9","unstructured":"Martens, J., Grosse, R.: Optimizing neural networks with Kronecker-factored approximate curvature. In: ICML, pp. 2408\u20132417 (2015)"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Xu, P., Roosta, F., Mahoney, M.W.: Second-order optimization for non-convex machine learning: an empirical study. In: Proceedings of the 2020 SIAM International Conference on Data Mining, pp. 199\u2013207 (2020)","DOI":"10.1137\/1.9781611976236.23"},{"key":"11_CR11","volume-title":"Numerical Optimization","author":"J Nocedal","year":"2006","unstructured":"Nocedal, J., Wright, S.J.: Numerical Optimization. Springer (2006)"},{"key":"11_CR12","unstructured":"Martens, J., Sutskever, I.: Hessian-free optimization for recurrent networks. In: ICML, pp. 1033\u20131040 (2011)"},{"issue":"2","key":"11_CR13","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"SI Amari","year":"1998","unstructured":"Amari, S.I.: Natural gradient in learning. Neural Comput. 10(2), 251\u2013276 (1998)","journal-title":"Neural Comput."},{"key":"11_CR14","unstructured":"Graves, A.: Generating sequences with recurrent networks. https:\/\/arxiv.org\/abs\/1308.0850 (2013)"},{"key":"11_CR15","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR16","unstructured":"Krizhevsky, A., Hinton, G.: Learning features from small images. Tech. Rep., Univ. Toronto (2009)"},{"key":"11_CR17","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks. https:\/\/arxiv.org\/abs\/1409.1556 (2014)"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, Z.: Deep residual learning. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR19","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L.: Densely connected networks. In: CVPR, pp. 4700\u20134708 (2017)"},{"issue":"2","key":"11_CR20","first-page":"313","volume":"19","author":"M Marcus","year":"1993","unstructured":"Marcus, M., Santorini, B., Marcinkiewicz, M.A.: The Penn Treebank. Comput. Linguist. 19(2), 313\u2013330 (1993)","journal-title":"Comput. Linguist."},{"key":"11_CR21","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.trc.2015.03.014","volume":"54","author":"X Ma","year":"2015","unstructured":"Ma, X., et al.: Long short-term memory for traffic prediction. Transp. Res. C. 54, 187\u2013197 (2015)","journal-title":"Transp. Res. C"},{"key":"11_CR22","unstructured":"Radford, A., et al.: Language models are unsupervised multitask learners. OpenAI Blog (2019)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3394-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T22:20:23Z","timestamp":1784326823000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3394-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,18]]},"ISBN":["9789819233939","9789819233946"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3394-6_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,18]]},"assertion":[{"value":"18 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}