{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:53:32Z","timestamp":1743134012573,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030786083"},{"type":"electronic","value":"9783030786090"}],"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.springer.com\/tdm"},{"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.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-78609-0_4","type":"book-chapter","created":{"date-parts":[[2021,7,8]],"date-time":"2021-07-08T23:38:40Z","timestamp":1625787520000},"page":"41-52","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Distributed Stochastic Gradient Descent Through Gaussian Averaging"],"prefix":"10.1007","author":[{"given":"Kaifan","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengkun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"En","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,9]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","unstructured":"Aji, K.A.F., Heafield, K.: Sparse communication for distributed gradient descent. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, pp. 440\u2013445 (2017). https:\/\/doi.org\/10.18653\/v1\/d17-1045","DOI":"10.18653\/v1\/d17-1045"},{"key":"4_CR2","unstructured":"Alistarh, D., Grubic, D., Li, J., Tomioka, R., Vojnovic, M.: QSGD: communication-efficient SGD via gradient quantization and encoding. In: Advances in Neural Information Processing Systems 30, pp. 1709\u20131720 (2017)"},{"key":"4_CR3","unstructured":"Bernstein, J., Wang, Y.X., Azizzadenesheli, K., Anandkumar, A.: signSGD: compressed optimisation for non-convex problems. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, vol. 80, pp. 560\u2013569. Stockholmsm\u00e4ssan, Stockholm, 10\u201315 July 2018"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Bottou, L.: Online learning and stochastic approximations (1998)","DOI":"10.1017\/CBO9780511569920.003"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C., Choi, J., Brand, D., Agrawal, A., Zhang, W., Gopalakrishnan, K.: AdaComp: adaptive residual gradient compression for data-parallel distributed training. In: 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, pp. 2827\u20132835, January 2018","DOI":"10.1609\/aaai.v32i1.11728"},{"key":"4_CR6","unstructured":"Dettmers, T.: 8-bit approximations for parallelism in deep learning. In: International Conference on Learning Representations (2016)"},{"key":"4_CR7","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2018)"},{"key":"4_CR8","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.90","DOI":"10.1109\/cvpr.2016.90"},{"key":"4_CR9","unstructured":"Johnson, R., Zhang, T.: Accelerating stochastic gradient descent using predictive variance reduction. In: Advances in Neural Information Processing Systems 26, pp. 315\u2013323 (2013)"},{"key":"4_CR10","unstructured":"Krizhevsky, A.: Learning Multiple Layers of Features from Tiny Images. University of Toronto, May 2012"},{"key":"4_CR11","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097\u20131105 (2012)"},{"key":"4_CR12","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., Dally, W.J.: Deep gradient compression: reducing the communication bandwidth for distributed training. In: International Conference on Learning Representations, May 2018"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Seide, F., Fu, H., Droppo, J., Li, G., Yu, D.: 1-bit stochastic gradient descent and application to data-parallel distributed training of speech DNNs. In: Interspeech 2014 (2014)","DOI":"10.21437\/Interspeech.2014-274"},{"key":"4_CR14","unstructured":"Shi, S., Chu, X., Cheung, K.C., See, S.: Understanding top-k sparsification in distributed deep learning. In: International Conference on Learning Representations (2020)"},{"key":"4_CR15","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations, May 2015"},{"key":"4_CR16","unstructured":"Stich, S.U., Cordonnier, J.B., Jaggi, M.: Sparsified SGD with memory. In: Advances in Neural Information Processing Systems 31, pp. 4447\u20134458 (2018)"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Strom, N.: Scalable distributed DNN training using commodity GPU cloud computing. In: INTERSPEECH, pp. 1488\u20131492 (2015)","DOI":"10.21437\/Interspeech.2015-354"},{"key":"4_CR18","unstructured":"Wangni, J., Wang, J., Liu, J., Zhang, T.: Gradient sparsification for communication-efficient distributed optimization. In: Advances in Neural Information Processing Systems 31, pp. 1299\u20131309 (2018)"},{"key":"4_CR19","unstructured":"Wen, W., et al.: TernGrad: ternary gradients to reduce communication in distributed deep learning. In: Advances in Neural Information Processing Systems 30, pp. 1509\u20131519 (2017)"},{"key":"4_CR20","unstructured":"Xu, H., et al.: Compressed communication for distributed deep learning: survey and quantitative evaluation. Technical report, KAUST, April 2020"},{"key":"4_CR21","unstructured":"Yu, Y., Wu, J., Huang, J.: Exploring fast and communication-efficient algorithms in large-scale distributed networks. In: Proceedings of Machine Learning Research, vol. 89, pp. 674\u2013683 (2019)"},{"key":"4_CR22","unstructured":"Zhou, S., Ni, Z., Zhou, X., Wen, H., Wu, Y., Zou, Y.: DoReFa-Net: training low bitwidth convolutional neural networks with low bitwidth gradients. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence and Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-78609-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,3]],"date-time":"2023-01-03T12:08:15Z","timestamp":1672747695000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-78609-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030786083","9783030786090"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-78609-0_4","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":"9 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICAIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence and Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dublin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ireland","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":"19 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"incodldos2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icaisconf.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}