{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T12:17:41Z","timestamp":1773058661231,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030014230","type":"print"},{"value":"9783030014247","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01424-7_39","type":"book-chapter","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T17:07:37Z","timestamp":1538413657000},"page":"392-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Width of Minima Reached by Stochastic Gradient Descent is Influenced by Learning Rate to Batch Size Ratio"],"prefix":"10.1007","author":[{"given":"Stanislaw","family":"Jastrz\u0119bski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zachary","family":"Kenton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Devansh","family":"Arpit","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Ballas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Asja","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yoshua","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amos","family":"Storkey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,27]]},"reference":[{"key":"39_CR1","unstructured":"Advani, M.S., Saxe, A.M.: High-dimensional dynamics of generalization error in neural networks. arXiv preprint arXiv:1710.03667 (2017)"},{"key":"39_CR2","unstructured":"Arpit, D., et al.: A closer look at memorization in deep networks. In: ICML (2017)"},{"issue":"9","key":"39_CR3","first-page":"142","volume":"17","author":"L Bottou","year":"1998","unstructured":"Bottou, L.: Online learning and stochastic approximations. On-line Learn. Neural netw. 17(9), 142 (1998)","journal-title":"On-line Learn. Neural netw."},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Chaudhari, P., Soatto, S.: Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks. arXiv:1710.11029 (2017)","DOI":"10.1109\/ITA.2018.8503224"},{"key":"39_CR5","unstructured":"Goyal, P., et al.: Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour. ArXiv e-prints (2017)"},{"issue":"1","key":"39_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/neco.1997.9.1.1","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Flat minima. Neural Comput. 9(1), 1\u201342 (1997)","journal-title":"Neural Comput."},{"key":"39_CR7","unstructured":"Hoffer, E., et al.: Train longer, generalize better: closing the generalization gap in large batch training of neural networks. ArXiv e-prints, arxiv:1705.08741"},{"key":"39_CR8","unstructured":"Junchi Li, C., et al.: Batch Size Matters: A Diffusion Approximation Framework on Nonconvex Stochastic Gradient Descent. ArXiv e-prints (2017)"},{"key":"39_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-12616-5","volume-title":"Numerical Solution of Stochastic Differential Equations","author":"Peter E. Kloeden","year":"1992","unstructured":"Kloeden, P.E., Platen, E.: Numerical Solution of Stochastic Differential Equations. Springer, Heidelberg (1992). https:\/\/doi.org\/10.1007\/978-3-662-12616-5"},{"key":"39_CR10","unstructured":"Kushner, H., Yin, G.: Stochastic Approximation and Recursive Algorithms and Applications (Stochastic Modelling and Applied Probability) (v. 35), 2nd edn. Springer (2003). http:\/\/www.amazon.com\/exec\/obidos\/redirect?tag=citeulike07-20&path=ASIN\/0387008942"},{"key":"39_CR11","unstructured":"Li, Q., Tai, C., E., W.: Stochastic modified equations and adaptive stochastic gradient algorithms. In: Proceedings of the 34th ICML (2017)"},{"key":"39_CR12","unstructured":"Mandt, S., Hoffman, M.D., Blei, D.M.: Stochastic gradient descent as approximate Bayesian inference. J. Mach. Learn. Res. 18, 134:1\u2013134:35 (2017)"},{"key":"39_CR13","unstructured":"Poggio, T., et al.: Theory of Deep Learning III: explaining the non-overfitting puzzle. ArXiv e-prints, ArXiv e-prints, arxiv:1801.00173 (2018)"},{"key":"39_CR14","unstructured":"Sagun, L., Evci, U., Ugur Guney, V., Dauphin, Y., Bottou, L.: Empirical Analysis Of The Hessian Of Over-parametrized Neural Networks. ArXiv e-prints (2017)"},{"key":"39_CR15","unstructured":"Shirish Keskar, N., Mudigere, D., Nocedal, J., Smelyanskiy, M., Tang, P.T.P.: On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. ArXiv e-prints (2016)"},{"key":"39_CR16","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint, arXiv:1409.1556 (2014)"},{"key":"39_CR17","unstructured":"Smith, S., Le, Q.: Understanding generalization and stochastic gradient descent. arXiv preprint, arXiv:1710.06451 (2017)"},{"key":"39_CR18","unstructured":"Welling, M., Teh, Y.W.: Bayesian learning via stochastic gradient Langevin dynamics. In: Proceedings of the 28th ICML, pp. 681\u2013688 (2011)"},{"key":"39_CR19","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. ArXiv e-prints (2017)"},{"key":"39_CR20","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., Vinyals, O.: Understanding deep learning requires rethinking generalization. arXiv preprint, arXiv:1611.03530 (2016)"},{"key":"39_CR21","unstructured":"Zhu, Z., Wu, J., Yu, B., Wu, L., Ma, J.: The Regularization Effects of Anisotropic Noise in Stochastic Gradient Descent. ArXiv e-prints (2018)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01424-7_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T09:33:39Z","timestamp":1773048819000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01424-7_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030014230","9783030014247"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01424-7_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"27 September 2018","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":"Rhodes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Open","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"360","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":"139","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":"28","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":"39% - 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":"2","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","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":"In addition there are 41 full poster papers and 11 short poster papers included in the proceedings","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)"}}]}}