{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:22:05Z","timestamp":1743106925096,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031478420"},{"type":"electronic","value":"9783031478437"}],"license":[{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:00:00Z","timestamp":1699315200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-47843-7_13","type":"book-chapter","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T21:27:25Z","timestamp":1699306045000},"page":"183-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Batch Level Distributed Training of\u00a0LSTM with\u00a0Infinity Norm Gradient Flow"],"prefix":"10.1007","author":[{"given":"Linzhe","family":"Cai","sequence":"first","affiliation":[]},{"given":"Chen","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xinghuo","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Chaojie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Andrew","family":"Eberhard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"13_CR1","unstructured":"Aggregated price and demand data (2023). https:\/\/aemo.com.au\/en\/energy-systems\/electricity"},{"key":"13_CR2","unstructured":"Bae, S.H., Choi, I.K., Kim, N.S.: Acoustic scene classification using parallel combination of LSTM and CNN. In: DCASE, pp. 11\u201315 (2016)"},{"key":"13_CR3","unstructured":"Box, G.E., Jenkins, G.M., Reinsel, G.C., Ljung, G.M.: Time Series Analysis: Forecasting and Control. John Wiley & Sons, Hoboken (2015)"},{"key":"13_CR4","unstructured":"Brownlee, J.: A gentle introduction to the rectified linear unit (ReLU). Mach. Learn. Mastery 6 (2019)"},{"key":"13_CR5","doi-asserted-by":"publisher","unstructured":"Cai, L., Yu, X., Li, C., Eberhard, A., Nguyen, L.T., Doan, C.T.: Impact of mathematical norms on convergence of gradient descent algorithms for deep neural networks learning. In: Aziz, H., Correa, D., French, T. (eds.) AI 2022: Advances in Artificial Intelligence. AI 2022. LNCS, vol. 13728, pp. 131\u2013144. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-22695-3_10","DOI":"10.1007\/978-3-031-22695-3_10"},{"key":"13_CR6","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.physa.2018.11.061","volume":"519","author":"J Cao","year":"2019","unstructured":"Cao, J., Li, Z., Li, J.: Financial time series forecasting model based on CEEMDAN and LSTM. Phys. A 519, 127\u2013139 (2019)","journal-title":"Phys. A"},{"key":"13_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101819","volume":"97","author":"Z Chen","year":"2023","unstructured":"Chen, Z., Ma, M., Li, T., Wang, H., Li, C.: Long sequence time-series forecasting with deep learning: a survey. Inf. Fusion 97, 101819 (2023)","journal-title":"Inf. Fusion"},{"key":"13_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, H.T., et al.: Wide & deep learning for recommender systems. In: Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, pp. 7\u201310 (2016)","DOI":"10.1145\/2988450.2988454"},{"key":"13_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.chaos.2020.109864","volume":"135","author":"VKR Chimmula","year":"2020","unstructured":"Chimmula, V.K.R., Zhang, L.: Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos, Solitons Fractals 135, 109864 (2020)","journal-title":"Chaos, Solitons Fractals"},{"key":"13_CR10","unstructured":"Conrad, K.: Equivalence of norms. Expository Paper, University of Connecticut, Storrs, heruntergeladen von, vol. 17, no. 2018 (2018)"},{"key":"13_CR11","unstructured":"Dean, J., et al.: Large scale distributed deep networks. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"13_CR12","unstructured":"developer, N.: System management interface SMI (2023). https:\/\/developer.nvidia.com\/nvidia-system-management-interface"},{"key":"13_CR13","unstructured":"(2023). www.tensorflow.org\/api_docs\/python\/tf\/distribute\/Strategy"},{"key":"13_CR14","doi-asserted-by":"publisher","first-page":"25111","DOI":"10.1109\/ACCESS.2020.2970836","volume":"8","author":"Y Fan","year":"2020","unstructured":"Fan, Y., Xu, K., Wu, H., Zheng, Y., Tao, B.: Spatiotemporal modeling for nonlinear distributed thermal processes based on kl decomposition, MLP and LSTM network. IEEE Access 8, 25111\u201325121 (2020)","journal-title":"IEEE Access"},{"key":"13_CR15","doi-asserted-by":"publisher","first-page":"31191","DOI":"10.1109\/ACCESS.2021.3060290","volume":"9","author":"B Farsi","year":"2021","unstructured":"Farsi, B., Amayri, M., Bouguila, N., Eicker, U.: On short-term load forecasting using machine learning techniques and a novel parallel deep LSTM-CNN approach. IEEE Access 9, 31191\u201331212 (2021)","journal-title":"IEEE Access"},{"issue":"10","key":"13_CR16","doi-asserted-by":"publisher","first-page":"2451","DOI":"10.1162\/089976600300015015","volume":"12","author":"FA Gers","year":"2000","unstructured":"Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: Continual prediction with LSTM. Neural Comput. 12(10), 2451\u20132471 (2000)","journal-title":"Neural Comput."},{"key":"13_CR17","doi-asserted-by":"crossref","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations. JHU Press, Baltimore (2013)","DOI":"10.56021\/9781421407944"},{"key":"13_CR18","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"issue":"8","key":"13_CR19","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"13_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"13_CR21","unstructured":"Micikevicius, P., et al.: Mixed precision training. arXiv preprint arXiv:1710.03740 (2017)"},{"key":"13_CR22","doi-asserted-by":"crossref","unstructured":"Mohanty, S.N., Lydia, E.L., Elhoseny, M., Al Otaibi, M.M.G., Shankar, K.: Deep learning with LSTM based distributed data mining model for energy efficient wireless sensor networks. Phys. Commun. 40, 101097 (2020)","DOI":"10.1016\/j.phycom.2020.101097"},{"key":"13_CR23","doi-asserted-by":"crossref","unstructured":"\u00d6zt\u00fcrk, M.M.: Hyperparameter optimization of a parallelized LSTM for time series prediction. Vietnam J. Comput. Sci. 1\u201326 (2023)","DOI":"10.1142\/S2196888823500033"},{"issue":"2","key":"13_CR24","doi-asserted-by":"publisher","first-page":"227","DOI":"10.3102\/1076998619872761","volume":"45","author":"B Pang","year":"2020","unstructured":"Pang, B., Nijkamp, E., Wu, Y.N.: Deep learning with tensorflow: a review. J. Educ. Behav. Stat. 45(2), 227\u2013248 (2020)","journal-title":"J. Educ. Behav. Stat."},{"key":"13_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2020.102662","volume":"163","author":"GDLT Parra","year":"2020","unstructured":"Parra, G.D.L.T., Rad, P., Choo, K.K.R., Beebe, N.: Detecting internet of things attacks using distributed deep learning. J. Netw. Comput. Appl. 163, 102662 (2020)","journal-title":"J. Netw. Comput. Appl."},{"key":"13_CR26","unstructured":"Parallel vs. distributed computing: an overview (2022). blog.purestorage.com\/purely-informational\/parallel-vs-distributed-computing-an-overview\/"},{"key":"13_CR27","unstructured":"Quinn, M.J.: Parallel Computing Theory and Practice. McGraw-Hill, Inc., New York (1994)"},{"key":"13_CR28","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.neucom.2018.09.082","volume":"323","author":"A Sagheer","year":"2019","unstructured":"Sagheer, A., Kotb, M.: Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 323, 203\u2013213 (2019)","journal-title":"Neurocomputing"},{"key":"13_CR29","unstructured":"Stollenga, M.F., Byeon, W., Liwicki, M., Schmidhuber, J.: Parallel multi-dimensional LSTM, with application to fast biomedical volumetric image segmentation. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"13_CR30","unstructured":"Better performance with tf.function (2023). www.tensorflow.org\/guide\/function"},{"key":"13_CR31","unstructured":"Ueno, Y., Fukuda, K.: Technologies behind distributed deep learning: Allreduce (2018)"},{"key":"13_CR32","unstructured":"Wilson, A.C., Mackey, L., Wibisono, A.: Accelerating rescaled gradient descent: fast optimization of smooth functions. Adv. Neural Inf. Process. Syst. 32 (2019)"}],"container-title":["Lecture Notes in Computer Science","Databases Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47843-7_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T21:33:13Z","timestamp":1699306393000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47843-7_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"ISBN":["9783031478420","9783031478437"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47843-7_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,11,7]]},"assertion":[{"value":"7 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Database Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adc2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"41","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":"26","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":"63% - 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":"2.5","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)"}}]}}