{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:12:21Z","timestamp":1750219941320,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,15]],"date-time":"2023-07-15T00:00:00Z","timestamp":1689379200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"South African National Research Foundation","award":["13819413"],"award-info":[{"award-number":["13819413"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,15]]},"DOI":"10.1145\/3583133.3596322","type":"proceedings-article","created":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T23:30:33Z","timestamp":1690241433000},"page":"2038-2046","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Quantifying and Visualizing the Sharpness of Attraction Basins in Neural Network Error Landscapes"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6615-1314","authenticated-orcid":false,"given":"Isobel","family":"Bosman","sequence":"first","affiliation":[{"name":"University of Pretoria, Pretoria, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3546-1467","authenticated-orcid":false,"given":"Anna Sergeevna","family":"Bosman","sequence":"additional","affiliation":[{"name":"University of Pretoria, Pretoria, South Africa"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6070-2632","authenticated-orcid":false,"given":"Katherine Mary","family":"Malan","sequence":"additional","affiliation":[{"name":"University of South Africa, Pretoria, South Africa"}]}],"member":"320","published-online":{"date-parts":[[2023,7,24]]},"reference":[{"volume-title":"Fitness landscape analysis of feed-forward neural networks. Ph. D. Dissertation","author":"Bosman Anna Sergeevna","key":"e_1_3_2_1_1_1","unstructured":"Anna Sergeevna Bosman . 2019. Fitness landscape analysis of feed-forward neural networks. Ph. D. Dissertation . University of Pretoria . Anna Sergeevna Bosman. 2019. Fitness landscape analysis of feed-forward neural networks. Ph. D. Dissertation. University of Pretoria."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7850152"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.113"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3208247"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1017\/9780511811487"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Machine Learning. PMLR, 1019--1028","author":"Dinh Laurent","year":"2017","unstructured":"Laurent Dinh , Razvan Pascanu , Samy Bengio , and Yoshua Bengio . 2017 . Sharp minima can generalize for deep nets . In International Conference on Machine Learning. PMLR, 1019--1028 . Laurent Dinh, Razvan Pascanu, Samy Bengio, and Yoshua Bengio. 2017. Sharp minima can generalize for deep nets. In International Conference on Machine Learning. PMLR, 1019--1028."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2003.808183"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899x\/420\/1\/012092"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/s0893-6080(97)00134-2"},{"key":"e_1_3_2_1_11_1","volume-title":"Asymmetric valleys: Beyond sharp and flat local minima. Advances in neural information processing systems 32","author":"He Haowei","year":"2019","unstructured":"Haowei He , Gao Huang , and Yang Yuan . 2019. Asymmetric valleys: Beyond sharp and flat local minima. Advances in neural information processing systems 32 ( 2019 ). Haowei He, Gao Huang, and Yang Yuan. 2019. Asymmetric valleys: Beyond sharp and flat local minima. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","author":"Hochreiter Sepp","year":"1994","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber . 1994. Simplifying Neural Nets by Discovering Flat Minima . In Advances in Neural Information Processing Systems , G. Tesauro, D. Touretzky, and T. Leen (Eds.), Vol. 7 . MIT Press . https:\/\/proceedings.neurips.cc\/paper\/ 1994 \/file\/01882513d5fa7c329e940dda99b12147-Paper.pdf Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1994. Simplifying Neural Nets by Discovering Flat Minima. In Advances in Neural Information Processing Systems, G. Tesauro, D. Touretzky, and T. Leen (Eds.), Vol. 7. MIT Press. https:\/\/proceedings.neurips.cc\/paper\/1994\/file\/01882513d5fa7c329e940dda99b12147-Paper.pdf"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/645513.657574"},{"key":"e_1_3_2_1_16_1","volume-title":"Leslie Pack Kaelbling, and Yoshua Bengio","author":"Kawaguchi Kenji","year":"2017","unstructured":"Kenji Kawaguchi , Leslie Pack Kaelbling, and Yoshua Bengio . 2017 . Generalization in deep learning. arXiv preprint arXiv:1710.05468 (2017). Kenji Kawaguchi, Leslie Pack Kaelbling, and Yoshua Bengio. 2017. Generalization in deep learning. arXiv preprint arXiv:1710.05468 (2017)."},{"key":"e_1_3_2_1_17_1","volume-title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima. ArXiv abs\/1609.04836","author":"Keskar Nitish Shirish","year":"2016","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. ArXiv abs\/1609.04836 ( 2016 ). 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. ArXiv abs\/1609.04836 (2016)."},{"key":"e_1_3_2_1_18_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). 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_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_1_20_1","unstructured":"Yann LeCun Corinna Cortes and Chris Burges. 2010. MNIST handwritten digit database. http:\/\/yann.lecun.com\/exdb\/mnist\/  Yann LeCun Corinna Cortes and Chris Burges. 2010. MNIST handwritten digit database. http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"e_1_3_2_1_21_1","volume-title":"Visualizing the loss landscape of neural nets. Advances in neural information processing systems 31","author":"Li Hao","year":"2018","unstructured":"Hao Li , Zheng Xu , Gavin Taylor , Christoph Studer , and Tom Goldstein . 2018. Visualizing the loss landscape of neural nets. Advances in neural information processing systems 31 ( 2018 ). Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018. Visualizing the loss landscape of neural nets. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/a14020040"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.04.015"},{"key":"e_1_3_2_1_24_1","volume-title":"Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378","author":"Nwankpa Chigozie","year":"2018","unstructured":"Chigozie Nwankpa , Winifred Ijomah , Anthony Gachagan , and Stephen Marshall . 2018. Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378 ( 2018 ). Chigozie Nwankpa, Winifred Ijomah, Anthony Gachagan, and Stephen Marshall. 2018. Activation functions: Comparison of trends in practice and research for deep learning. arXiv preprint arXiv:1811.03378 (2018)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3323383"},{"key":"e_1_3_2_1_26_1","volume-title":"A comprehensive survey on fitness landscape analysis. Recent advances in intelligent engineering systems","author":"Pitzer Erik","year":"2012","unstructured":"Erik Pitzer and Michael Affenzeller . 2012. A comprehensive survey on fitness landscape analysis. Recent advances in intelligent engineering systems ( 2012 ), 161--191. Erik Pitzer and Michael Affenzeller. 2012. A comprehensive survey on fitness landscape analysis. Recent advances in intelligent engineering systems (2012), 161--191."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ukci.2010.5625595"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45692-9_10"},{"key":"e_1_3_2_1_30_1","volume-title":"International Conference on Machine Learning. PMLR, 22325--22341","author":"Vlaar Tiffany J","year":"2022","unstructured":"Tiffany J Vlaar and Jonathan Frankle . 2022 . What can linear interpolation of neural network loss landscapes tell us? . In International Conference on Machine Learning. PMLR, 22325--22341 . Tiffany J Vlaar and Jonathan Frankle. 2022. What can linear interpolation of neural network loss landscapes tell us?. In International Conference on Machine Learning. PMLR, 22325--22341."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.87.23.9193"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the XI International Congress of Genetics 8","author":"Wright S.","year":"1932","unstructured":"S. Wright . 1932 . The Roles of Mutation, Inbreeding, crossbreeding and Selection in Evolution . Proceedings of the XI International Congress of Genetics 8 (1932), 209--222. S. Wright. 1932. The Roles of Mutation, Inbreeding, crossbreeding and Selection in Evolution. Proceedings of the XI International Congress of Genetics 8 (1932), 209--222."},{"key":"e_1_3_2_1_33_1","volume-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747","author":"Xiao Han","year":"2017","unstructured":"Han Xiao , Kashif Rasul , and Roland Vollgraf . 2017. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 ( 2017 ). Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)."}],"event":{"name":"GECCO '23 Companion: Companion Conference on Genetic and Evolutionary Computation","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"location":"Lisbon Portugal","acronym":"GECCO '23 Companion"},"container-title":["Proceedings of the Companion Conference on Genetic and Evolutionary Computation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583133.3596322","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583133.3596322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:54Z","timestamp":1750182534000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583133.3596322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,15]]},"references-count":32,"alternative-id":["10.1145\/3583133.3596322","10.1145\/3583133"],"URL":"https:\/\/doi.org\/10.1145\/3583133.3596322","relation":{},"subject":[],"published":{"date-parts":[[2023,7,15]]},"assertion":[{"value":"2023-07-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}