{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:18:49Z","timestamp":1783610329090,"version":"3.55.0"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"MLEDGE project","award":["REGAGE22e00052829516"],"award-info":[{"award-number":["REGAGE22e00052829516"]}]},{"name":"Ministry of Economic Affairs and Digital Transformation and the European Union-NextGenerationEU\/PRTR"},{"name":"NSF","award":["1956393 and 1900654"],"award-info":[{"award-number":["1956393 and 1900654"]}]},{"name":"UC Noyce Foundation gift"},{"name":"NSF Award","award":["1956393"],"award-info":[{"award-number":["1956393"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Model. Perform. Eval. Comput. Syst."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Model pruning has been proposed as a technique for reducing the size and complexity of Federated Learning (FL) models. By making local models coarser, pruning is intuitively expected to improve protection against privacy attacks. However, the level of this expected privacy protection has not been previously characterized, or optimized jointly with utility.<\/jats:p>\n          <jats:p>\n            In this article, we first characterize the privacy offered by pruning. We establish information-theoretic upper bounds on the information leakage from pruned FL and experimentally validate them under state-of-the-art privacy attacks across different FL pruning schemes. Second, we introduce\n            <jats:italic>PriPrune<\/jats:italic>\n            \u2014a privacy-aware algorithm for pruning in FL.\n            <jats:italic>PriPrune<\/jats:italic>\n            uses defense pruning masks, which can be applied locally after\n            <jats:italic>any<\/jats:italic>\n            pruning algorithm, and adapts the defense pruning rate to jointly optimize privacy and accuracy. Another key idea in the design of\n            <jats:italic>PriPrune<\/jats:italic>\n            is\n            <jats:italic>Pseudo-Pruning<\/jats:italic>\n            : it undergoes defense pruning within the local model and only sends the pruned model to the server, whereas the weights pruned out by the defense mask are withheld locally for future local training rather than being removed. We show that\n            <jats:italic>PriPrune<\/jats:italic>\n            significantly improves the privacy-accuracy tradeoff compared to state-of-the-art pruned FL schemes. For example, on the FEMNIST dataset,\n            <jats:italic>PriPrune<\/jats:italic>\n            improves the privacy of PruneFL by 45.5% without reducing accuracy.\n          <\/jats:p>","DOI":"10.1145\/3702241","type":"journal-article","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T08:46:51Z","timestamp":1730537211000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learning"],"prefix":"10.1145","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2178-840X","authenticated-orcid":false,"given":"Tianyue","family":"Chu","sequence":"first","affiliation":[{"name":"IMDEA Networks Institute, Madrid (Leganes), Spain and Universidad Carlos III de Madrid, Madrid (Leganes), Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4775-5406","authenticated-orcid":false,"given":"Mengwei","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California Irvine, Irvine, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7361-106X","authenticated-orcid":false,"given":"Nikolaos","family":"Laoutaris","sequence":"additional","affiliation":[{"name":"IMDEA Networks Institute, Madrid (Leganes) Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1803-8675","authenticated-orcid":false,"given":"Athina","family":"Markopoulou","sequence":"additional","affiliation":[{"name":"University of California Irvine, Irvine, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,5,30]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"Philip Bachman R. Devon Hjelm and William Buchwalter. 2019. Learning representations by maximizing mutual information across views. Advances in Neural Information Processing Systems 32 (2019) 1\u201311. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/ddf354219aac374f1d40b7e760ee5bb7-Paper.pdf"},{"key":"e_1_3_3_3_2","unstructured":"Mohamed Ishmael Belghazi Aristide Baratin Sai Rajeshwar Sherjil Ozair Yoshua Bengio Aaron Courville and Devon Hjelm. 2018. Mutual information neural estimation. In Proceedings of the 35th International Conference on Machine Learning Vol. 80. 531\u2013540. https:\/\/proceedings.mlr.press\/v80\/belghazi18a.html"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i6.20555"},{"key":"e_1_3_3_5_2","first-page":"1175","volume-title":"Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS \u201917)","author":"Bonawitz Keith","year":"2017","unstructured":"Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2017. Practical secure aggregation for privacy-preserving machine learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS \u201917). ACM, New York, NY, USA, 1175\u20131191. DOI:10.1145\/3133956.3133982"},{"key":"e_1_3_3_6_2","unstructured":"Sebastian Caldas Sai Meher Karthik Duddu Peter Wu Tian Li Jakub Kone\u010dn\u1ef3 H. Brendan McMahan Virginia Smith and Ameet Talwalkar. 2018. LEAF: A benchmark for federated settings. arXiv:1812.01097 (2018)."},{"key":"e_1_3_3_7_2","first-page":"15834","article-title":"The lottery ticket hypothesis for pre-trained BERT networks","volume":"33","author":"Chen Tianlong","year":"2020","unstructured":"Tianlong Chen, Jonathan Frankle, Shiyu Chang, Sijia Liu, Yang Zhang, Zhangyang Wang, and Michael Carbin. 2020. The lottery ticket hypothesis for pre-trained BERT networks. Advances in Neural Information Processing Systems 33 (2020), 15834\u201315846.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_8_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR \u201920)","author":"Du Min","year":"2020","unstructured":"Min Du, Ruoxi Jia, and Dawn Song. 2020. Robust anomaly detection and backdoor attack detection via differential privacy. In Proceedings of the 8th International Conference on Learning Representations (ICLR \u201920). https:\/\/openreview.net\/forum?id=SJx0q1rtvS"},{"key":"e_1_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Cynthia Dwork. 2006. Differential privacy. In Automata Languages and Programming. Lecture Notes in Computer Science Vol. 4052. Springer 1\u201312.","DOI":"10.1007\/11787006_1"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.56553\/POPETS-2023-0030"},{"key":"e_1_3_3_11_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR \u201919)","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle and Michael Carbin. 2019. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In Proceedings of the 7th International Conference on Learning Representations (ICLR \u201919). https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"e_1_3_3_12_2","first-page":"16937","article-title":"Inverting gradients\u2014How easy is it to break privacy in federated learning?","volume":"33","author":"Geiping Jonas","year":"2020","unstructured":"Jonas Geiping, Hartmut Bauermeister, Hannah Dr\u00f6ge, and Michael Moeller. 2020. Inverting gradients\u2014How easy is it to break privacy in federated learning? Advances in Neural Information Processing Systems 33 (2020), 16937\u201316947.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_13_2","unstructured":"Antonious Girgis Deepesh Data Suhas Diggavi Peter Kairouz and Ananda Theertha Suresh. 2021. Shuffled model of differential privacy in federated learning. In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics Vol. 130. 2521\u20132529. https:\/\/proceedings.mlr.press\/v130\/girgis21a.html"},{"key":"e_1_3_3_14_2","unstructured":"Song Han Huizi Mao and William J. Dally. 2016. Deep compression: Compressing deep neural network with pruning trained quantization and Huffman coding. In Proceedings of the 4th International Conference on Learning Representations (ICLR \u201916): Conference Track. http:\/\/arxiv.org\/abs\/1510.00149"},{"key":"e_1_3_3_15_2","unstructured":"Song Han Jeff Pool John Tran and William J. Dally. 2015. Learning both weights and connections for efficient neural networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS \u201915) Vol. 1. 1135\u20131143."},{"key":"e_1_3_3_16_2","unstructured":"Alexander Herzog Robbie Southam Ioannis Mavromatis and Aftab Khan. 2024. FedMap: Iterative magnitude-based pruning for communication-efficient federated learning. arXiv:2406.19850 (2024)."},{"key":"e_1_3_3_17_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Jang Eric","year":"2017","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2017. Categorical reparameterization with Gumbel-Softmax. In Proceedings of the International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rkE3y85ee"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3166101"},{"issue":"1","key":"e_1_3_3_19_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, H. Brendan McMahan, Brendan Avent, Aur\u00e9lien Bellet, Mehdi Bennis, Arjun Nitin Bhagoji, Kallista Bonawitz, Zachary Charles, Graham Cormode, Rachel Cummings, Rafael G. L. D\u2019Oliveira, Hubert Eichner, Salim El Rouayheb, David Evans, Josh Gardner, Zachary Garrett, Adria Gascon, Badih Ghazi, Phillip B. Gibbons, Marco Gruteser, Zaid Harchaoui, Chaoyang He, Lie He, Zhouyuan Huo, Ben Hutchinson, Justin Hsu, Martin Jaggi, Tara Javidi, Gauri Joshi, Mikhail Khodak, Jakub Konecny, Aleksandra Korolova, Farinaz Koushanfar, Sanmi Koyejo, Tancrede Lepoint, Yang Liu, Prateek Mittal, Mehryar Mohri, Richard Nock, Ayfer Ozgur, Rasmus Pagh, Hang Qi, Daniel Ramage, Ramesh Raskar, Mariana Raykova, Dawn Song, Weikang Song, Sebastian U. Stich, Ziteng Sun, Ananda Theertha Suresh, Florian Tramer, Praneeth Vepakomma, Jianyu Wang, Li Xiong, Zheng Xu, Qiang Yang, Felix X. Yu, Han Yu, and Sen Zhao. 2021. Advances and open problems in federated learning. Foundations and Trends\u00ae in Machine Learning 14, 1\u20132 (2021), 1\u2013210.","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"e_1_3_3_20_2","volume-title":"Learning Multiple Layers of Features from Tiny Images","year":"2009","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto, Toronto, ON, Canada. https:\/\/www.cs.toronto.edu\/kriz\/learning-features-2009-TR.pdf"},{"key":"e_1_3_3_21_2","unstructured":"Yann LeCun John S. Denker and Sara A. Solla. 1989. Optimal brain damage. Advances in Neural Information Processing Systems 2 (1989) 598\u2013605. http:\/\/papers.nips.cc\/paper\/250-optimal-brain-damage"},{"key":"e_1_3_3_22_2","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR \u201919)","author":"Lee Namhoon","year":"2019","unstructured":"Namhoon Lee, Thalaiyasingam Ajanthan, and Philip H. S. Torr. 2019. SNIP: Single-shot network pruning based on connection sensitivity. In Proceedings of the 7th International Conference on Learning Representations (ICLR \u201919). https:\/\/openreview.net\/forum?id=B1VZqjAcYX"},{"key":"e_1_3_3_23_2","unstructured":"Ang Li Jingwei Sun Binghui Wang Lin Duan Sicheng Li Yiran Chen and Hai Li. 2020. LotteryFL: Personalized and communication-efficient federated learning with lottery ticket hypothesis on non-IID datasets. arXiv:2008.03371 (2020)."},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_3_3_25_2","first-page":"12749","article-title":"Sanity checks for lottery tickets: Does your winning ticket really win the jackpot?","volume":"34","author":"Ma Xiaolong","year":"2021","unstructured":"Xiaolong Ma, Geng Yuan, Xuan Shen, Tianlong Chen, Xuxi Chen, Xiaohan Chen, Ning Liu, Minghai Qin, Sijia Liu, Zhangyang Wang, and Yanzhi Wang. 2021. Sanity checks for lottery tickets: Does your winning ticket really win the jackpot? Advances in Neural Information Processing Systems 34 (2021), 12749\u201312760.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_26_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR \u201917): Conference Track","author":"Maddison Chris J.","year":"2017","unstructured":"Chris J. Maddison, Andriy Mnih, and Yee Whye Teh. 2017. The concrete distribution: A continuous relaxation of discrete random variables. In Proceedings of the 5th International Conference on Learning Representations (ICLR \u201917): Conference Track. https:\/\/openreview.net\/forum?id=S1jE5L5gl"},{"key":"e_1_3_3_27_2","unstructured":"Brendan McMahan Eider Moore Daniel Ramage Seth Hampson and Blaise Ag\u00fcera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS \u201917). 1273\u20131282. http:\/\/proceedings.mlr.press\/v54\/mcmahan17a.html"},{"key":"e_1_3_3_28_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR \u201918): Conference Track","author":"McMahan H. Brendan","year":"2018","unstructured":"H. Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang. 2018. Learning differentially private recurrent language models. In Proceedings of the 6th International Conference on Learning Representations (ICLR \u201918): Conference Track. https:\/\/openreview.net\/forum?id=BJ0hF1Z0b"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Jun-Hyung Park Yeachan Kim Junho Kim Joon-Young Choi and SangKeun Lee. 2023. Dynamic structure pruning for compressing CNNs. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI \u201923) the 35th Conference on Innovative Applications of Artificial Intelligence (IAAI \u201923) and the 13th Symposium on Educational Advances in Artificial Intelligence (EAAI \u201923). 9408\u20139416. DOI:10.1609\/AAAI.V37I8.26127","DOI":"10.1609\/AAAI.V37I8.26127"},{"key":"e_1_3_3_30_2","unstructured":"PyTorch. n.d. Gumbel Softmax in PyTorch Documentation. Retrieved November 5 2024 from https:\/\/pytorch.org\/docs\/stable\/generated\/torch.nn.functional.gumbel_softmax.html"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3370967"},{"key":"e_1_3_3_32_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the 3rd International Conference on Learning Representations (ICLR \u201915): Conference Track. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Jinhyun So Ramy E. Ali Basak G\u00fcler Jiantao Jiao and Amir Salman Avestimehr. 2023. Securing secure aggregation: Mitigating multi-round privacy leakage in federated learning. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI \u201923). 9864\u20139873. DOI:10.1609\/AAAI.V37I8.26177","DOI":"10.1609\/AAAI.V37I8.26177"},{"key":"e_1_3_3_34_2","first-page":"694","article-title":"LightSecAgg: A lightweight and versatile design for secure aggregation in federated learning","volume":"4","author":"So Jinhyun","year":"2022","unstructured":"Jinhyun So, Chaoyang He, Chien-Sheng Yang, Songze Li, Qian Yu, Ramy E Ali, Basak Guler, and Salman Avestimehr. 2022. LightSecAgg: A lightweight and versatile design for secure aggregation in federated learning. Proceedings of Machine Learning and Systems 4 (2022), 694\u2013720.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_3_35_2","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS \u201920)","author":"Tanaka Hidenori","year":"2020","unstructured":"Hidenori Tanaka, Daniel Kunin, Daniel L. K. Yamins, and Surya Ganguli. 2020. Pruning neural networks without any data by iteratively conserving synaptic flow. In Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS \u201920). Article 535, 13 pages."},{"key":"e_1_3_3_36_2","unstructured":"Joy A. Thomas and Thomas M. Cover. 2006. Elements of Information Theory. John Wiley & Sons."},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","unstructured":"Aleksei Triastcyn and Boi Faltings. 2019. Federated learning with Bayesian differential privacy. In Proceedings of the 2019 IEEE International Conference on Big Data (BigData \u201919). 2587\u20132596. DOI:10.1109\/BIGDATA47090.2019.9005465","DOI":"10.1109\/BIGDATA47090.2019.9005465"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","unstructured":"Georgia Tsaloli Bei Liang Carlo Brunetta Gustavo Banegas and Aikaterini Mitrokotsa. 2021. DEVA: Decentralized verifiable secure aggregation for privacy-preserving learning. In Information Security. Lecture Notes in Computer Science Vol. 13118. Springer 296\u2013319. DOI:10.1007\/978-3-030-91356-4_16","DOI":"10.1007\/978-3-030-91356-4_16"},{"key":"e_1_3_3_39_2","volume-title":"Proceedings of the 8th International Conference on Learning Representations (ICLR \u201920)","author":"Wang Chaoqi","year":"2020","unstructured":"Chaoqi Wang, Guodong Zhang, and Roger B. Grosse. 2020. Picking winning tickets before training by preserving gradient flow. In Proceedings of the 8th International Conference on Learning Representations (ICLR \u201920). https:\/\/openreview.net\/forum?id=SkgsACVKPH"},{"key":"e_1_3_3_40_2","first-page":"1","volume-title":"Proceedings of the 2020 IEEE Global Communications Conference (GLOBECOM \u201920)","author":"Wu Danye","year":"2020","unstructured":"Danye Wu, Miao Pan, Zhiwei Xu, Yujun Zhang, and Zhu Han. 2020. Towards efficient secure aggregation for model update in federated learning. In Proceedings of the 2020 IEEE Global Communications Conference (GLOBECOM \u201920). IEEE, 1\u20136. DOI:10.1109\/GLOBECOM42002.2020.9347960"},{"key":"e_1_3_3_41_2","first-page":"72181","article-title":"Dynamic personalized federated learning with adaptive differential privacy","volume":"36","author":"Yang Xiyuan","year":"2023","unstructured":"Xiyuan Yang, Wenke Huang, and Mang Ye. 2023. Dynamic personalized federated learning with adaptive differential privacy. Advances in Neural Information Processing Systems 36 (2023), 72181\u201372192.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_3_42_2","first-page":"16332","volume-title":"Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201921)","author":"Yin Hongxu","year":"2021","unstructured":"Hongxu Yin, Arun Mallya, Arash Vahdat, Jose M. Alvarez, Jan Kautz, and Pavlo Molchanov. 2021. See through gradients: Image batch recovery via GradInversion. In Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR \u201921). IEEE, 16332\u201316341. DOI:10.1109\/CVPR46437.2021.01607"},{"key":"e_1_3_3_43_2","first-page":"6381","volume-title":"Proceedings of the 32nd USENIX Security Symposium (USENIX Security \u201923)","author":"Yue Kai","year":"2023","unstructured":"Kai Yue, Richeng Jin, Chau-Wai Wong, Dror Baron, and Huaiyu Dai. 2023. Gradient obfuscation gives a false sense of security in federated learning. In Proceedings of the 32nd USENIX Security Symposium (USENIX Security \u201923). 6381\u20136398. https:\/\/www.usenix.org\/conference\/usenixsecurity23\/presentation\/yue"},{"key":"e_1_3_3_44_2","first-page":"26048","volume-title":"Proceedings of the International Conference on Machine Learning (ICML \u201922)","volume":"162","author":"Zhang Xinwei","year":"2022","unstructured":"Xinwei Zhang, Xiangyi Chen, Mingyi Hong, Zhiwei Steven Wu, and Jinfeng Yi. 2022. Understanding clipping for federated learning: Convergence and client-level differential privacy. In Proceedings of the International Conference on Machine Learning (ICML \u201922), Vol. 162. 26048\u201326067."},{"key":"e_1_3_3_45_2","unstructured":"Bo Zhao Konda Reddy Mopuri and Hakan Bilen. 2020. iDLG: Improved deep leakage from gradients. arXiv:cs.LG\/2001.02610 (2020)."},{"key":"e_1_3_3_46_2","first-page":"11","volume-title":"Deep Leakage from Gradients","author":"Zhu Ligeng","year":"2019","unstructured":"Ligeng Zhu, Zhijian Liu, and Song Han. 2019. Deep Leakage from Gradients. Curran Associates, Red Hook, NY, USA, 11."},{"key":"e_1_3_3_47_2","article-title":"The anisotropic noise in stochastic gradient descent: Its behavior of escaping from sharp minima and regularization effects","author":"Zhu Zhanxing","year":"2019","unstructured":"Zhanxing Zhu, Jingfeng Wu, Bing Yu, Lei Wu, and Jinwen Ma. 2019. The anisotropic noise in stochastic gradient descent: Its behavior of escaping from sharp minima and regularization effects. In Proceedings of the 36th International Conference on Machine Learning. 7654\u20137663. https:\/\/proceedings.mlr.press\/v97\/zhu19e.html","journal-title":"Proceedings of the 36th International Conference on Machine Learning."}],"container-title":["ACM Transactions on Modeling and Performance Evaluation of Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702241","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3702241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:31Z","timestamp":1750295431000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702241"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1145\/3702241"],"URL":"https:\/\/doi.org\/10.1145\/3702241","relation":{},"ISSN":["2376-3639","2376-3647"],"issn-type":[{"value":"2376-3639","type":"print"},{"value":"2376-3647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]},"assertion":[{"value":"2024-04-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}