{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:27:01Z","timestamp":1778758021625,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,23]]},"DOI":"10.1145\/3746467.3801522","type":"proceedings-article","created":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:32Z","timestamp":1778756792000},"page":"205-210","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GPU Starvation from the Control Plane: A Systems Study of Reinforcement Learning in Deep Learning Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7019-1979","authenticated-orcid":false,"given":"Michael","family":"Seavers","sequence":"first","affiliation":[{"name":"Western Kentucky University, Bowling Green, KY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8559-1801","authenticated-orcid":false,"given":"Yongyi","family":"Gong","sequence":"additional","affiliation":[{"name":"Guangdong University of Foreign Studies, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5554-5647","authenticated-orcid":false,"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Sciences, Western Kentucky University, Bowling Green, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Corrado Alessio. [n. d.]. Animal-10. https:\/\/www.kaggle.com\/datasets\/alessiocorrado99\/animals10\/discussion\/117317"},{"key":"e_1_3_2_1_2_1","unstructured":"Amazon. [n. d.]. Amazon EC2 P3dn Instances. https:\/\/aws.amazon.com\/ec2\/instance-types\/p3\/"},{"key":"e_1_3_2_1_3_1","first-page":"397","article-title":"Using Confidence Bounds for Exploitation-Exploration Trade-Offs","author":"Auer Peter","year":"2002","unstructured":"Peter Auer. 2002. Using Confidence Bounds for Exploitation-Exploration Trade-Offs. Journal of Machine Learning Research 3, Nov (2002), 397\u2013422.","journal-title":"Journal of Machine Learning Research 3"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 208\u2013214","author":"Chu Wei","year":"2011","unstructured":"Wei Chu, Lihong Li, Lev Reyzin, and Robert Schapire. 2011. Contextual Bandits with Linear Payoff Functions. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 208\u2013214."},{"key":"e_1_3_2_1_5_1","volume-title":"Deep Learning Workload Scheduling in GPU Datacenters: Taxonomy, Challenges, and Vision. arXiv preprint arXiv:2205.11913","author":"Gao Wei","year":"2022","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 preprint arXiv:2205.11913 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639232"},{"key":"e_1_3_2_1_7_1","volume-title":"Pipedream: Fast and Efficient Pipeline Parallel DNN Training. https:\/\/arxiv.org\/abs","author":"Harlap Aaron","year":"2018","unstructured":"Aaron Harlap, Deepak Narayanan, Amar Phanishayee, Vivek Seshadri, Nikhil Devanur, Greg Ganger, and Phil Gibbons. 2018. Pipedream: Fast and Efficient Pipeline Parallel DNN Training. https:\/\/arxiv.org\/abs"},{"key":"e_1_3_2_1_8_1","volume-title":"Squeeze-and-Excitation Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7132\u20137141","author":"Hu Jie","year":"2018","unstructured":"Jie Hu, Li Shen, and Gang Sun. 2018. Squeeze-and-Excitation Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7132\u20137141."},{"key":"e_1_3_2_1_9_1","volume-title":"Gpipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Advances in Neural Information Processing Systems 32.","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Dehao Chen, Mia Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V Le, Yonghui Wu, et al. 2019. Gpipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism. Advances in Neural Information Processing Systems 32."},{"key":"e_1_3_2_1_10_1","volume-title":"The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems. arXiv preprint arXiv:2012.04210","author":"Inci Ahmet","year":"2020","unstructured":"Ahmet Inci, Evgeny Bolotin, Yaosheng Fu, Gal Dalal, Shie Mannor, David Nellans, and Diana Marculescu. 2020. The Architectural Implications of Distributed Reinforcement Learning on CPU-GPU Systems. arXiv preprint arXiv:2012.04210 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, 93\u2013105","author":"Jangda Abhinav","year":"2024","unstructured":"Abhinav Jangda, Saeed Maleki, Maryam Mehri Dehnavi, Madan Musuvathi, and Olli Saarikivi. 2024. A Framework for Fine-Grained Synchronization of Dependent GPU Kernels. In 2024 IEEE\/ACM International Symposium on Code Generation and Optimization (CGO). IEEE, 93\u2013105."},{"key":"e_1_3_2_1_12_1","volume-title":"Bpipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models. In International Conference on Machine Learning. PMLR, 16639\u201316653","author":"Kim Taebum","year":"2023","unstructured":"Taebum Kim, Hyoungjoo Kim, Gyeong-In Yu, and Byung-Gon Chun. 2023. Bpipe: Memory-Balanced Pipeline Parallelism for Training Large Language Models. In International Conference on Machine Learning. PMLR, 16639\u201316653."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_6"},{"key":"e_1_3_2_1_14_1","volume-title":"The Epoch-Greedy Algorithm for Multi-Armed Bandits with Side Information. Advances in Neural Information Processing Systems 20","author":"Langford John","year":"2007","unstructured":"John Langford and Tong Zhang. 2007. The Epoch-Greedy Algorithm for Multi-Armed Bandits with Side Information. Advances in Neural Information Processing Systems 20 (2007)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_3_2_1_16_1","volume-title":"An Empirical Model of Large-Batch Training. arXiv preprint arXiv:1812.06162","author":"McCandlish Sam","year":"2018","unstructured":"Sam McCandlish, Jared Kaplan, Dario Amodei, and OpenAI Dota Team. 2018. An Empirical Model of Large-Batch Training. arXiv preprint arXiv:1812.06162 (2018)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2788396"},{"key":"e_1_3_2_1_18_1","volume-title":"Asynchronous Methods for Deep Reinforcement Learning. In International Conference on Machine Learning. PmLR","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adria Puigdomenech Badia, Mehdi Mirza, Alex Graves, Timothy Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. In International Conference on Machine Learning. PmLR, 1928\u20131937."},{"key":"e_1_3_2_1_19_1","volume-title":"Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, et al.","author":"Nair Arun","year":"2015","unstructured":"Arun Nair, Praveen Srinivasan, Sam Blackwell, Cagdas Alcicek, Rory Fearon, Alessandro De Maria, Vedavyas Panneershelvam, Mustafa Suleyman, Charles Beattie, Stig Petersen, et al. 2015. Massively Parallel Methods for Deep Reinforcement Learning. arXiv preprint arXiv:1507.04296 (2015)."},{"key":"e_1_3_2_1_20_1","volume-title":"An Overview of the Data-Loader Landscape: Comparative Performance Analysis. In 2024 IEEE International Conference on Big Data (BigData). IEEE, 360\u2013367","author":"Ofeidis Iason","year":"2024","unstructured":"Iason Ofeidis, Diego Kiedanski, and Leandros Tassiulas. 2024. An Overview of the Data-Loader Landscape: Comparative Performance Analysis. In 2024 IEEE International Conference on Big Data (BigData). IEEE, 360\u2013367."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.suscom.2018.07.010"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3749185"},{"key":"e_1_3_2_1_23_1","volume-title":"Brice Videau, and Kai Shu.","author":"Xu Xiongxiao","year":"2024","unstructured":"Xiongxiao Xu, Solomon Abera Bekele, Brice Videau, and Kai Shu. 2024. Online Energy Optimization in GPUs: A Multi-armed Bandit Approach. arXiv preprint arXiv:2410.11855 (2024)."},{"key":"e_1_3_2_1_24_1","volume-title":"Large Batch Training of Convolutional Networks. arXiv preprint arXiv:1708.03888","author":"You Yang","year":"2017","unstructured":"Yang You, Igor Gitman, and Boris Ginsburg. 2017. Large Batch Training of Convolutional Networks. arXiv preprint arXiv:1708.03888 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Scaling SGD Batch Size to 32k for ImageNet Training. arXiv preprint arXiv:1708.03888 6, 12","author":"You Yang","year":"2017","unstructured":"Yang You, Igor Gitman, and Boris Ginsburg. 2017. Scaling SGD Batch Size to 32k for ImageNet Training. arXiv preprint arXiv:1708.03888 6, 12 (2017), 6."},{"key":"e_1_3_2_1_26_1","volume-title":"Importance of Data Loading Pipeline in Training Deep Neural Networks. arXiv preprint arXiv:2005.02130","author":"Zolnouri Mahdi","year":"2020","unstructured":"Mahdi Zolnouri, Xinlin Li, and Vahid Partovi Nia. 2020. Importance of Data Loading Pipeline in Training Deep Neural Networks. arXiv preprint arXiv:2005.02130 (2020)."}],"event":{"name":"ACMSE 2026: 2026 ACM Southeast Conference","location":"Troy University Troy AL USA","acronym":"ACMSE 2026"},"container-title":["Proceedings of the 2026 ACM Southeast Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746467.3801522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:06:42Z","timestamp":1778756802000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746467.3801522"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,23]]},"references-count":26,"alternative-id":["10.1145\/3746467.3801522","10.1145\/3746467"],"URL":"https:\/\/doi.org\/10.1145\/3746467.3801522","relation":{},"subject":[],"published":{"date-parts":[[2026,4,23]]},"assertion":[{"value":"2026-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}