{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:25:32Z","timestamp":1743013532998,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030676605"},{"type":"electronic","value":"9783030676612"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-67661-2_3","type":"book-chapter","created":{"date-parts":[[2021,2,24]],"date-time":"2021-02-24T07:10:26Z","timestamp":1614150626000},"page":"35-51","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Momentum Coefficient for Neural Network Optimization"],"prefix":"10.1007","author":[{"given":"Zana","family":"Rashidi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kasra","family":"Ahmadi K. A.","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aijun","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaogang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,25]]},"reference":[{"issue":"2","key":"3_CR1","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1162\/089976698300017746","volume":"10","author":"SI Amari","year":"1998","unstructured":"Amari, S.I.: Natural gradient works efficiently in learning. Neural Comput. 10(2), 251\u2013276 (1998)","journal-title":"Neural Comput."},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Aujol, J.F., Rondepierre, A., Aujol, J., Dossal, C., et al.: Optimal convergence rates for Nesterov acceleration. arXiv preprint arXiv:1805.05719 (2018)","DOI":"10.1137\/18M1186757"},{"issue":"2","key":"3_CR3","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1137\/16M1080173","volume":"60","author":"L Bottou","year":"2018","unstructured":"Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223\u2013311 (2018)","journal-title":"SIAM Rev."},{"key":"3_CR4","unstructured":"Defazio, A.: On the curved geometry of accelerated optimization. arXiv preprint arXiv:1812.04634 (2018)"},{"key":"3_CR5","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12(Jul), 2121\u20132159 (2011)"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Ghadimi, E., Feyzmahdavian, H.R., Johansson, M.: Global convergence of the heavy-ball method for convex optimization. In: 2015 European Control Conference (ECC), pp. 310\u2013315. IEEE (2015)","DOI":"10.1109\/ECC.2015.7330562"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504\u2013507 (2006)","DOI":"10.1126\/science.1127647"},{"key":"3_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"3_CR10","unstructured":"Lucas, J., Sun, S., Zemel, R., Grosse, R.: Aggregated momentum: stability through passive damping. arXiv preprint arXiv:1804.00325 (2018)"},{"key":"3_CR11","unstructured":"Martens, J.: Deep learning via hessian-free optimization. In: ICML, vol. 27, pp. 735\u2013742 (2010)"},{"key":"3_CR12","unstructured":"Martens, J., Grosse, R.: Optimizing neural networks with Kronecker-Factored approximate curvature. In: International Conference on Machine Learning, pp. 2408\u20132417 (2015)"},{"key":"3_CR13","unstructured":"Meng, X., Chen, H.: Accelerating Nesterov\u2019s method for strongly convex functions with Lipschitz gradient. arXiv preprint arXiv:1109.6058 (2011)"},{"key":"3_CR14","unstructured":"Merity, S., Keskar, N.S., Socher, R.: Regularizing and optimizing LSTM language models. arXiv preprint arXiv:1708.02182 (2017)"},{"key":"3_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization: A Basic Course","author":"Y Nesterov","year":"2013","unstructured":"Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-1-4419-8853-9"},{"key":"3_CR16","unstructured":"Nesterov, Y.E.: A method for solving the convex programming problem with convergence rate o $$(1\/\\text{k}^2)$$. Dokl. akad. nauk Sssr. 269, 543\u2013547 (1983)"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"O\u2019donoghue, B., Candes, E.: Adaptive restart for accelerated gradient schemes. Found. Comput. Math. 15(3), 715\u2013732 (2015)","DOI":"10.1007\/s10208-013-9150-3"},{"issue":"5","key":"3_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4(5), 1\u201317 (1964)","journal-title":"USSR Comput. Math. Math. Phys."},{"key":"3_CR19","unstructured":"Reddi, S.J., Kale, S., Kumar, S.: On the convergence of ADAM and beyond (2018)"},{"key":"3_CR20","unstructured":"Su, W., Boyd, S., Candes, E.: A differential equation for modeling Nesterov\u2019s accelerated gradient method: theory and insights. In: Advances in Neural Information Processing Systems, pp. 2510\u20132518 (2014)"},{"key":"3_CR21","unstructured":"Sutskever, I., Martens, J., Dahl, G.E., Hinton, G.E.: On the importance of initialization and momentum in deep learning. In: ICML (3), vol. 28, pp. 1139\u20131147 (2013)"},{"key":"3_CR22","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4(2), 26\u201331 (2012)"},{"key":"3_CR23","doi-asserted-by":"crossref","unstructured":"Wibisono, A., Wilson, A.C., Jordan, M.I.: A variational perspective on accelerated methods in optimization. Proc. Natl. Acad. Sci. 113(47), E7351\u2013E7358 (2016)","DOI":"10.1073\/pnas.1614734113"},{"key":"3_CR24","unstructured":"Zeiler, M.D.: Adadelta: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-67661-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,23]],"date-time":"2025-02-23T23:01:58Z","timestamp":1740351718000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-67661-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030676605","9783030676612"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-67661-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"25 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ghent","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd2020.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"945","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"195","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"21% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4,5","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4,4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference took place virtually due to the COVID-19 pandemic","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}