{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:23:08Z","timestamp":1773156188815,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030661502","type":"print"},{"value":"9783030661519","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","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":[[2020]]},"DOI":"10.1007\/978-3-030-66151-9_19","type":"book-chapter","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T00:02:47Z","timestamp":1608508967000},"page":"296-309","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Pre-interpolation Loss Behavior in Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-8711","authenticated-orcid":false,"given":"Arthur E. W.","family":"Venter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7456-7769","authenticated-orcid":false,"given":"Marthinus W.","family":"Theunissen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3103-5858","authenticated-orcid":false,"given":"Marelie H.","family":"Davel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,12,21]]},"reference":[{"key":"19_CR1","unstructured":"Ba, J., Erdogdu, M., Suzuki, T., Wu, D., Zhang, T.: Generalization of two-layer neural networks: an asymptotic viewpoint. In: International Conference on Learning Representations (2020)"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"15849","DOI":"10.1073\/pnas.1903070116","volume":"116","author":"M Belkin","year":"2019","unstructured":"Belkin, M., Hsu, D., Ma, S., Mandal, S.: Reconciling modern machine-learning practice and the classical bias-variance trade-off. Proc. Natl. Acad. Sci. 116, 15849\u201315854 (2019)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"19_CR3","unstructured":"d\u2019Ascoli, S., Refinetti, M., Biroli, G., Krzakala, F.: Double trouble in double descent: bias and variance(s) in the lazy regime. In: Thirty-seventh International Conference on Machine Learning, pp. 2676\u20132686 (2020)"},{"key":"19_CR4","unstructured":"Devore, J., Farnum, N.R.: Applied Statistics for Engineers and Scientists. Thomson Brooks\/Cole, Belmont (2005)"},{"key":"19_CR5","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http:\/\/www.deeplearningbook.org"},{"key":"19_CR6","unstructured":"Goodfellow, I.J., Vinyals, O.: Qualitatively characterizing neural network optimization problems. CoRR abs\/1412.6544 (2015)"},{"key":"19_CR7","unstructured":"Hardt, M., Recht, B., Singer, Y.: Train faster, generalize better: stability of stochastic gradient descent. In: International Conference on Machine Learning, pp. 1225\u20131234. PMLR (2016)"},{"key":"19_CR8","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Improving neural networks by preventing co-adaptation of feature detectors. CoRR abs\/1207.0580 (2012). http:\/\/arxiv.org\/abs\/1207.0580"},{"key":"19_CR9","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\u201342 (1997)","journal-title":"Neural Comput."},{"key":"19_CR10","unstructured":"Hoffer, E., Hubara, I., Soudry, D.: Train longer, generalize better: closing the generalization gap in large batch training of neural networks. In: Advances in Neural Information Processing Systems, pp. 1731\u20131741 (2017)"},{"key":"19_CR11","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, 2015, Lille, France, 6\u201311 July 2015. JMLR Workshop and Conference Proceedings, vol. 37, pp. 448\u2013456. JMLR.org (2015)"},{"key":"19_CR12","doi-asserted-by":"publisher","unstructured":"Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132324 (1998). https:\/\/doi.org\/10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"19_CR13","unstructured":"Martin, C., Mahoney, M.: Implicit self-regularization in deep neural networks: evidence from random matrix theory and implications for learning. ArXiv abs\/1810.01075 (2018)"},{"key":"19_CR14","unstructured":"Murphy, K.P.: Machine Learning: A Probabilistic Perspective. The MIT Press, Cambridge (2012)"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Nakkiran, P., Kaplun, G., Bansal, Y., Yang, T., Barak, B., Sutskever, I.: Deep double descent: where bigger models and more data hurt. In: International Conference on Learning Representations (2020)","DOI":"10.1088\/1742-5468\/ac3a74"},{"key":"19_CR16","unstructured":"Nakkiran, P., Venkat, P., Kakade, S.M., Ma, T.: Optimal regularization can mitigate double descent. ArXiv abs\/2003.01897 (2020)"},{"key":"19_CR17","unstructured":"Neyshabur, B., Tomioka, R., Srebro, N.: In search of the real inductive bias: on the role of implicit regularization in deep learning. CoRR abs\/1412.6614 (2015)"},{"key":"19_CR18","unstructured":"Novak, R., Bahri, Y., Abolafia, D.A., Pennington, J., Sohl-Dickstein, J.: Sensitivity and generalization in neural networks: an empirical study. In: International Conference on Learning Representations (2018)"},{"key":"19_CR19","doi-asserted-by":"publisher","first-page":"4265","DOI":"10.1109\/TSP.2017.2708039","volume":"65","author":"J Sokolic","year":"2017","unstructured":"Sokolic, J., Giryes, R., Sapiro, G., Rodrigues, M.: Robust large margin deep neural networks. IEEE Trans. Signal Process. 65, 4265\u20134280 (2017)","journal-title":"IEEE Trans. Signal Process."},{"issue":"10","key":"19_CR20","doi-asserted-by":"publisher","first-page":"1429","DOI":"10.1016\/S0893-6080(03)00138-2","volume":"16","author":"DR Wilson","year":"2003","unstructured":"Wilson, D.R., Martinez, T.: The general inefficiency of batch training for gradient descent learning. Neural Netw. Off. J. Int. Neural Netw. Soc. 16(10), 1429\u201351 (2003)","journal-title":"Neural Netw. Off. J. Int. Neural Netw. Soc."},{"key":"19_CR21","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR abs\/1708.07747 (2017). http:\/\/arxiv.org\/abs\/1708.07747"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66151-9_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T22:10:40Z","timestamp":1670451040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66151-9_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030661502","9783030661519"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66151-9_19","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"21 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SACAIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Southern African Conference for Artificial Intelligence Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Muldersdrift","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"South Africa","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 February 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 February 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sacair2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/sacair.org.za\/","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":"53","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":"19","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":"36% - 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":"3","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":"3","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":"Dur to the COVID-19 pandemic SACAIR 2020 was postponed to February 2021","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)"}}]}}