{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T20:40:02Z","timestamp":1755981602412,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T00:00:00Z","timestamp":1702252800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,11]]},"DOI":"10.1145\/3631310.3633489","type":"proceedings-article","created":{"date-parts":[[2024,1,20]],"date-time":"2024-01-20T00:20:38Z","timestamp":1705710038000},"page":"7-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward Competitive Serverless Deep Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0149-6645","authenticated-orcid":false,"given":"Stefan","family":"Petrescu","sequence":"first","affiliation":[{"name":"Leibniz University Hannover"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0031-2921","authenticated-orcid":false,"given":"Diego Albo","family":"Martinez","sequence":"additional","affiliation":[{"name":"Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3791-7114","authenticated-orcid":false,"given":"Jan S.","family":"Rellermeyer","sequence":"additional","affiliation":[{"name":"Leibniz University Hannover"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2951913.2976746"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Ali Ahsan","year":"2020","unstructured":"Ahsan Ali, Riccardo Pinciroli, Feng Yan, and Evgenia Smirni. 2020. Batch: Machine Learning Inference Serving on Serverless Platforms with Adaptive Batching. In Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (Atlanta, Georgia) (SC '20). IEEE Press, Article 69, 15 pages."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 12th USENIX Conference on Hot Topics in Cloud Computing (HotCloud'20)","author":"Berral Josep L.","year":"2020","unstructured":"Josep L. Berral, Chen Wang, and Alaa Youssef. 2020. AI4DL: Mining Behaviors of Deep Learning Workloads for Resource Management. In Proceedings of the 12th USENIX Conference on Hot Topics in Cloud Computing (HotCloud'20). USENIX Association, USA, Article 3, 1 pages."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2019.00-10"},{"key":"e_1_3_2_1_5_1","unstructured":"Sebastian B\u00f6hm and Guido Wirtz. 2021. Profiling Lightweight Container Platforms: MicroK8s and K3s in Comparison to Kubernetes.. In ZEUS. 65--73."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.07316"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MLHPC54614.2021.00008"},{"volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Brown Tom B.","key":"e_1_3_2_1_8_1","unstructured":"Tom B. et al. Brown. 2020. Language Models Are Few-Shot Learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems (Vancouver, BC, Canada) (NIPS'20). Curran Associates Inc., Article 159, 25 pages."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362711"},{"key":"e_1_3_2_1_10_1","unstructured":"Wei Gao Qinghao Hu Zhisheng Ye Peng Sun Xiaolin Wang Yingwei Luo Tianwei Zhang and Yonggang Wen. 2022. Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy Challenges and Vision. arXiv:2205.11913 [cs.DC]"},{"volume-title":"Deep Learning","author":"Goodfellow Ian J.","key":"e_1_3_2_1_11_1","unstructured":"Ian J. Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, Cambridge, MA, USA. http:\/\/www.deeplearningbook.org."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. https:\/\/doi.org\/10.48550\/ARXIV.1512.03385","DOI":"10.48550\/ARXIV.1512.03385"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177732.3177734"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Vatche Isahagian Vinod Muthusamy and Aleksander Slominski. 2018. Serving Deep Learning Models in a Serverless Platform. 257--262. https:\/\/doi.org\/10.1109\/IC2E.2018.00052","DOI":"10.1109\/IC2E.2018.00052"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3459240"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Peter H. Jin Qiaochu Yuan Forrest Iandola and Kurt Keutzer. 2016. How to scale distributed deep learning? https:\/\/doi.org\/10.48550\/ARXIV.1611.04581","DOI":"10.48550\/ARXIV.1611.04581"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3127479.3128601"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Nitish Shirish Keskar Dheevatsa Mudigere Jorge Nocedal Mikhail Smelyanskiy and Ping Tak Peter Tang. 2016. On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. https:\/\/doi.org\/10.48550\/ARXIV.1609.04836","DOI":"10.48550\/ARXIV.1609.04836"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP2018.2018.00090"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1901.02244"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/UCC-Companion.2018.00051"},{"key":"e_1_3_2_1_22_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1-4.541"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3508360"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1808.07217"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3344341.3368814"},{"key":"e_1_3_2_1_27_1","first-page":"1","article-title":"Overview of Amazon Web Services","volume":"105","author":"Mathew Sajee","year":"2014","unstructured":"Sajee Mathew and J Varia. 2014. Overview of Amazon Web Services. Amazon Whitepapers 105 (2014), 1--22.","journal-title":"Amazon Whitepapers"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CloudCom2018.2018.00033"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2020.01.004"},{"volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","key":"e_1_3_2_1_30_1","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32. Curran Associates, Inc., 8024--8035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the 16th USENIX Conference on Networked Systems Design and Implementation","author":"Pu Qifan","year":"2019","unstructured":"Qifan Pu, Shivaram Venkataraman, and Ion Stoica. 2019. Shuffling, Fast and Slow: Scalable Analytics on Serverless Infrastructure. In Proceedings of the 16th USENIX Conference on Networked Systems Design and Implementation (Boston, MA, USA) (NSDI'19). USENIX Association, USA, 193--206."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Maithra Raghu Ben Poole Jon Kleinberg Surya Ganguli and Jascha Sohl-Dickstein. 2016. On the Expressive Power of Deep Neural Networks. https:\/\/doi.org\/10.48550\/ARXIV.1606.05336","DOI":"10.48550\/ARXIV.1606.05336"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3419111.3421287"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","unstructured":"Sebastian U. Stich. 2018. Local SGD Converges Fast and Communicates Little. https:\/\/doi.org\/10.48550\/ARXIV.1805.09767","DOI":"10.48550\/ARXIV.1805.09767"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","unstructured":"Zhenheng Tang Shaohuai Shi Xiaowen Chu Wei Wang and Bo Li. 2020. Communication-Efficient Distributed Deep Learning: A Comprehensive Survey. https:\/\/doi.org\/10.48550\/ARXIV.2003.06307","DOI":"10.48550\/ARXIV.2003.06307"},{"volume-title":"Is big data performance reproducible in modern cloud networks?.In 17th USENIX symposium on networked systems design and implementation (NSDI 20). 513--527","author":"Uta Alexandru","key":"e_1_3_2_1_36_1","unstructured":"Alexandru Uta, Alexandru Custura, Dmitry Duplyakin, Ivo Jimenez, Jan Rellermeyer, Carlos Maltzahn, Robert Ricci, and Alexandru Iosup. 2020. Is big data performance reproducible in modern cloud networks?.In 17th USENIX symposium on networked systems design and implementation (NSDI 20). 513--527."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Chengyi Wang Sanyuan Chen Yu Wu Ziqiang Zhang Long Zhou Shujie Liu Zhuo Chen Yanqing Liu Huaming Wang Jinyu Li Lei He Sheng Zhao and Furu Wei. 2023. Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers. https:\/\/doi.org\/10.48550\/ARXIV.2301.02111","DOI":"10.48550\/ARXIV.2301.02111"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737391"},{"volume-title":"Case study: Performance evaluation of Kind. Bachelor's Thesis","author":"Bor\u00e9n Fabian Waxin","key":"e_1_3_2_1_39_1","unstructured":"Fabian Waxin Bor\u00e9n. 2021. Case study: Performance evaluation of Kind. Bachelor's Thesis. KTH Royal Institute of Technology."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3368474.3368498"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3054656"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00020"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/447"},{"key":"e_1_3_2_1_44_1","volume-title":"Culotta (Eds.)","volume":"23","author":"Zinkevich Martin","year":"2010","unstructured":"Martin Zinkevich, Markus Weimer, Lihong Li, and Alex Smola. 2010. Parallelized Stochastic Gradient Descent. In Advances in Neural Information Processing Systems, J. Lafferty, C. Williams, J. Shawe-Taylor, R. Zemel, and A. Culotta (Eds.), Vol. 23. Curran Associates, Inc."}],"event":{"name":"Middleware '23: 24th International Middleware Conference","sponsor":["ACM Association for Computing Machinery","IFIP International Federation for Information Processing"],"location":"Bologna Italy","acronym":"Middleware '23"},"container-title":["Proceedings of the 4th International Workshop on Distributed Infrastructure for the Common Good"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631310.3633489","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3631310.3633489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T20:26:13Z","timestamp":1755980773000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3631310.3633489"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,11]]},"references-count":44,"alternative-id":["10.1145\/3631310.3633489","10.1145\/3631310"],"URL":"https:\/\/doi.org\/10.1145\/3631310.3633489","relation":{},"subject":[],"published":{"date-parts":[[2023,12,11]]},"assertion":[{"value":"2024-01-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}