{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T12:02:28Z","timestamp":1764331348384,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,14]]},"DOI":"10.1145\/3712255.3734344","type":"proceedings-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T15:14:02Z","timestamp":1754925242000},"page":"2301-2308","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Visualising Adam Oscillations in Neural Network Loss Landscapes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5449-335X","authenticated-orcid":false,"given":"Henri","family":"van der Grijp","sequence":"first","affiliation":[{"name":"University of Pretoria, Pretoria, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3546-1467","authenticated-orcid":false,"given":"Anna S.","family":"Bosman","sequence":"additional","affiliation":[{"name":"University of Pretoria, Pretoria, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-2632","authenticated-orcid":false,"given":"Katherine M.","family":"Malan","sequence":"additional","affiliation":[{"name":"University of South Africa, Pretoria, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of machine learning and systems 2","author":"Blalock Davis","year":"2020","unstructured":"Davis Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John Guttag. 2020. What is the state of neural network pruning? Proceedings of machine learning and systems 2 (2020), 129\u2013146."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.113"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583133.3596321"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"e_1_3_2_1_6_1","volume-title":"NeurIPS Workshop on Heavy Tails in Machine Learning.","author":"Cohen Jeremy","year":"2023","unstructured":"Jeremy Cohen, Behrooz Ghorbani, Shankar Krishnan, Naman Agarwal, Sourabh Medapati, Michal Badura, Daniel Suo, Zachary Nado, George E Dahl, and Justin Gilmer. 2023. Adaptive Gradient Methods at the Edge of Stability. In NeurIPS Workshop on Heavy Tails in Machine Learning."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_8_1","volume-title":"Trainable Neural Networks. In International Conference on Learning Representations.","author":"Frankle Jonathan","year":"2018","unstructured":"Jonathan Frankle and Michael Carbin. 2018. The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_9_1","volume-title":"Daniel M Roy, and Michael Carbin.","author":"Frankle Jonathan","year":"2019","unstructured":"Jonathan Frankle, Gintare Karolina Dziugaite, Daniel M Roy, and Michael Carbin. 2019. Stabilizing the lottery ticket hypothesis. arXiv preprint arXiv:1903.01611 (2019)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IV55152.2023.10186819"},{"key":"e_1_3_2_1_13_1","volume-title":"5th International Conference on Learning Representations, ICLR","author":"Keskar Nitish Shirish","year":"2017","unstructured":"Nitish Shirish Keskar, Jorge Nocedal, Ping Tak Peter Tang, Dheevatsa Mudigere, and Mikhail Smelyanskiy. 2017. On large-batch training for deep learning: Generalization gap and sharp minima. In 5th International Conference on Learning Representations, ICLR 2017."},{"key":"e_1_3_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_15_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Learning Representations.","author":"Lee N","year":"2019","unstructured":"N Lee, T Ajanthan, S Gould, and PHS Torr. 2019. A signal propagation perspective for pruning neural networks at initialization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_18_1","volume-title":"Exploring Gradient Oscillation in Deep Neural Network Training. In 2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton). IEEE, 1\u20137.","author":"Morchdi Chedi","year":"2023","unstructured":"Chedi Morchdi, Yi Zhou, Jie Ding, and Bei Wang. 2023. Exploring Gradient Oscillation in Deep Neural Network Training. In 2023 59th Annual Allerton Conference on Communication, Control, and Computing (Allerton). IEEE, 1\u20137."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1919995117"},{"key":"e_1_3_2_1_20_1","volume-title":"International Conference on Learning Representations.","author":"Wang Chaoqi","year":"2020","unstructured":"Chaoqi Wang, Guodong Zhang, and Roger Grosse. 2020. Picking Winning Tickets Before Training by Preserving Gradient Flow. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","volume-title":"Can Deniz Bezek, and Orcun Goksel","author":"Zhu Lingkai","year":"2024","unstructured":"Lingkai Zhu, Can Deniz Bezek, and Orcun Goksel. 2024. FGGP: Fixed-Rate Gradient-First Gradual Pruning. arXiv preprint arXiv:2411.05500 (2024)."}],"event":{"name":"GECCO '25 Companion: Genetic and Evolutionary Computation Conference Companion","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"location":"NH Malaga Hotel Malaga Spain","acronym":"GECCO '25 Companion"},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference Companion"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712255.3734344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T11:47:06Z","timestamp":1759837626000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712255.3734344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,14]]},"references-count":21,"alternative-id":["10.1145\/3712255.3734344","10.1145\/3712255"],"URL":"https:\/\/doi.org\/10.1145\/3712255.3734344","relation":{},"subject":[],"published":{"date-parts":[[2025,7,14]]},"assertion":[{"value":"2025-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}