{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T22:51:53Z","timestamp":1743029513161,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030623647"},{"type":"electronic","value":"9783030623654"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/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":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-62365-4_33","type":"book-chapter","created":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T06:02:51Z","timestamp":1603951371000},"page":"348-355","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Stateful Optimization in Federated Learning of Neural Networks"],"prefix":"10.1007","author":[{"given":"P\u00e9ter","family":"Kiss","sequence":"first","affiliation":[]},{"given":"Tom\u00e1\u0161","family":"Horv\u00e1th","sequence":"additional","affiliation":[]},{"given":"Vukasin","family":"Felbab","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,27]]},"reference":[{"key":"33_CR1","unstructured":"Keras reference model for cifar-10. https:\/\/keras.io\/examples\/cifar10_cnn\/. Accessed 04 Feb 2020"},{"key":"33_CR2","unstructured":"Keras reference model for mnist. https:\/\/keras.io\/examples\/mnist_mlp\/. Accessed 04 Feb 2020"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Zhou, F. Cong, G.: On the convergence properties of a k-step averaging stochastic gradient descent algorithm for nonconvex optimization (2017)","DOI":"10.24963\/ijcai.2018\/447"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Yu, H., Yang, S., Zhu, S.: Parallel restarted SGD with faster convergence and less communication: demystifying why model averaging works for deep learning, vol. 33 (2019)","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"33_CR5","unstructured":"Chen, J., Pan, X., Monga, R., Bengio, S., Jozefowicz, R.: Revisiting distributed synchronous SGD. arXiv preprint arXiv:1604.00981 (2016)"},{"key":"33_CR6","unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: Advances in Neural Information Processing Systems, pp. 1223\u20131231 (2012)"},{"key":"33_CR7","unstructured":"Felbab, V., Kiss, P., Horv\u00e1th, T.: Optimization in federated learning. In: CEUR Workshop Proceedings (CEUR-WS.org), vol. 2473, pp. 58\u201365. ceur-ws.org (2019). ISSN: 1613\u20130073"},{"key":"33_CR8","unstructured":"Goyal, P., et al.: Accurate, large minibatch SGD: training imagenet in 1 hour. arXiv preprint arXiv:1706.02677 (2017)"},{"key":"33_CR9","unstructured":"Hard, A., et al.: Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604 (2018)"},{"key":"33_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":"33_CR11","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. arXiv preprint arXiv:1609.04836 (2016)"},{"key":"33_CR12","unstructured":"Khaled, A., Mishchenko, K., Richt\u00e1rik, P.: First analysis of local gd on heterogeneous data (2019)"},{"key":"33_CR13","unstructured":"Kone\u010dn\u00fd, J., McMahan, H.B., Ramage, D., Richt\u00e1rik, P.: Federated optimization: distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527 (2016)"},{"key":"33_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-642-35289-8_3","volume-title":"Neural Networks: Tricks of the Trade","author":"YA LeCun","year":"2012","unstructured":"LeCun, Y.A., Bottou, L., Orr, G.B., M\u00fcller, K.-R.: Efficient backProp. In: Montavon, G., Orr, G.B., M\u00fcller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 9\u201348. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-35289-8_3"},{"key":"33_CR15","unstructured":"Li, T., Sahu, A.K., Zaheer, M., Sanjabi, M., Talwalkar, A., Smith, V.: Federated optimization in heterogeneous networks (2018)"},{"key":"33_CR16","unstructured":"Li, X., Huang, K., Yang, W., Wang, S., Zhang, Z.: On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189 (2019)"},{"key":"33_CR17","unstructured":"Liu, W., Chen, L., Chen, Y., Zhang, W.: Accelerating federated learning via momentum gradient descent. arXiv preprint arXiv:1910.03197 (2019)"},{"key":"33_CR18","unstructured":"Masters, D., Luschi, C.: Revisiting small batch training for deep neural networks. arXiv preprint arXiv:1804.07612 (2018)"},{"key":"33_CR19","unstructured":"McMahan, H.B., Moore, E., Ramage, D., Hampson, S., et al.: Communication-efficient learning of deep networks from decentralized data. arXiv preprint arXiv:1602.05629 (2016)"},{"key":"33_CR20","unstructured":"Stich, S.U.: Local SGD converges fast and communicates little (2018)"},{"key":"33_CR21","unstructured":"Wang, J., Joshi, G.: Cooperative SGD: a unified framework for the design and analysis of communication-efficient SGD algorithms (2018)"},{"key":"33_CR22","unstructured":"Wang, K., Mathews, R., Kiddon, C., Eichner, H., Beaufays, F., Ramage, D.: Federated evaluation of on-device personalization. arXiv preprint arXiv:1910.10252 (2019)"},{"key":"33_CR23","unstructured":"Wang, S., et al.: Adaptive federated learning in resource constrained edge computing systems. In: IEEE INFOCOM 2018-IEEE Conference on Computer Communications (2018)"},{"key":"33_CR24","unstructured":"Woodworth, B., Wang, J., Smith, A., McMahan, B., Srebro, N.: Graph oracle models, lower bounds, and gaps for parallel stochastic optimization (2018)"},{"key":"33_CR25","unstructured":"Yurochkin, M., Agarwal, M., Ghosh, S., Greenewald, K., Hoang, T.N., Khazaeni, Y.: Bayesian nonparametric federated learning of neural networks. arXiv preprint arXiv:1905.12022 (2019)"},{"key":"33_CR26","unstructured":"Zhang, S., Choromanska, A.E., LeCun, Y.: Deep learning with elastic averaging SGD. In: Advances in Neural Information Processing Systems, pp. 685\u2013693 (2015)"},{"key":"33_CR27","unstructured":"Zhao, Y., Li, M., Lai, L., Suda, N., Civin, D., Chandra, V.: Federated learning with non-iid data. arXiv preprint arXiv:1806.00582 (2018)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-62365-4_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:07:22Z","timestamp":1710266842000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-62365-4_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030623647","9783030623654"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-62365-4_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"27 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IDEAL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Data Engineering and Automated Learning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guimaraes","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"4 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ideal2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/islab.di.uminho.pt\/ideal2020\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"134","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":"93","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":"69% - 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":"2.8","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":"Yes","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 was held 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)"}}]}}