{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:15:02Z","timestamp":1750220102196,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,6,24]],"date-time":"2022-06-24T00:00:00Z","timestamp":1656028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,6,24]]},"DOI":"10.1145\/3548608.3559206","type":"proceedings-article","created":{"date-parts":[[2022,10,14]],"date-time":"2022-10-14T17:47:01Z","timestamp":1665769621000},"page":"274-278","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Truncated Cross-entropy: A New Loss Function for Multi-category Classification"],"prefix":"10.1145","author":[{"given":"Yaolin","family":"Zheng","sequence":"first","affiliation":[{"name":"Computer school, Beijing Information Science and Technology University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbo","family":"Huang","sequence":"additional","affiliation":[{"name":"Computer school, Beijing Information Science and Technology University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoxu","family":"Yan","sequence":"additional","affiliation":[{"name":"Computer school, Beijing Information Science and Technology University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayu","family":"He","sequence":"additional","affiliation":[{"name":"Computer school, Beijing Information Science and Technology University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,14]]},"reference":[{"key":"#cr-split#-e_1_3_2_1_1_1.1","doi-asserted-by":"crossref","unstructured":"Qian N. 1999. On the momentum term in gradient descent learning algorithms. J. Neural networks 12 1 145-151. https:\/\/doi.org\/10.1016\/S0893-6080(98)00116-6 10.1016\/S0893-6080(98)00116-6","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"#cr-split#-e_1_3_2_1_1_1.2","doi-asserted-by":"crossref","unstructured":"Qian N. 1999. On the momentum term in gradient descent learning algorithms. J. Neural networks 12 1 145-151. https:\/\/doi.org\/10.1016\/S0893-6080(98)00116-6","DOI":"10.1016\/S0893-6080(98)00116-6"},{"key":"e_1_3_2_1_2_1","first-page":"7","article-title":"Adaptive subgradient methods for online learning and stochastic optimization. J","volume":"12","author":"Duchi J","year":"2011","unstructured":"Duchi J , Hazan E , Singer Y. 2011 . Adaptive subgradient methods for online learning and stochastic optimization. J . Journal of machine learning research , 12 , 7 Duchi J, Hazan E, Singer Y. 2011. Adaptive subgradient methods for online learning and stochastic optimization. J. Journal of machine learning research, 12, 7","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_3_1","unstructured":"Zeiler M D. 2012. Adadelta: an adaptive learning rate method. arXiv:1212.5701. Retrieved from https:\/\/arxiv.org\/abs\/1212.5701  Zeiler M D. 2012. Adadelta: an adaptive learning rate method. arXiv:1212.5701. Retrieved from https:\/\/arxiv.org\/abs\/1212.5701"},{"volume-title":"Ba J 2015. Adam: a Method for Stochastic Optimization. Interna-tional Conference on Learning Representations, 1-13","author":"Kingma D P","key":"e_1_3_2_1_4_1","unstructured":"Kingma D P , Ba J 2015. Adam: a Method for Stochastic Optimization. Interna-tional Conference on Learning Representations, 1-13 . Kingma D P, Ba J 2015. Adam: a Method for Stochastic Optimization. Interna-tional Conference on Learning Representations, 1-13."},{"key":"e_1_3_2_1_5_1","unstructured":"De S Mukherjee A Ullah E. 2018. Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration. arXiv:1807.06766. Retrieved from https:\/\/arxiv.org\/abs\/1807.06766  De S Mukherjee A Ullah E. 2018. Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration. arXiv:1807.06766. Retrieved from https:\/\/arxiv.org\/abs\/1807.06766"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_1_7_1","unstructured":"Beyer L H\u00e9naff O J Kolesnikov A 2020. Are we done with imagenet? arXiv:2006.07159. Retrieved from https:\/\/arxiv.org\/abs\/2006.07159  Beyer L H\u00e9naff O J Kolesnikov A 2020. Are we done with imagenet? arXiv:2006.07159. Retrieved from https:\/\/arxiv.org\/abs\/2006.07159"},{"key":"e_1_3_2_1_8_1","volume-title":"Analysis and optimization of loss functions for multiclass, top-k, and multilabel classification","author":"Lapin M","year":"2017","unstructured":"Lapin M , Hein M , Schiele B. 2017. Analysis and optimization of loss functions for multiclass, top-k, and multilabel classification . J. IEEE transactions on pattern analysis and machine intelligence, 40, 7, 1533-1554. https:\/\/doi.org\/10.1109\/TPAMI. 2017 .2751607 10.1109\/TPAMI.2017.2751607 Lapin M, Hein M, Schiele B. 2017. Analysis and optimization of loss functions for multiclass, top-k, and multilabel classification. J. IEEE transactions on pattern analysis and machine intelligence, 40, 7, 1533-1554. https:\/\/doi.org\/10.1109\/TPAMI.2017.2751607"},{"key":"e_1_3_2_1_9_1","unstructured":"Brian Lucena. 2022. Loss Functions for Classification using Structured Entropy. arXiv:2206.07122. Retrieved from https:\/\/arxiv.org\/abs\/2206.07122  Brian Lucena. 2022. Loss Functions for Classification using Structured Entropy. arXiv:2206.07122. Retrieved from https:\/\/arxiv.org\/abs\/2206.07122"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01252"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, 2206-2212","author":"Feng L","year":"2021","unstructured":"Feng L , Shu S , Lin Z , 2021 . Can cross entropy loss be robust to label noise? In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, 2206-2212 . Feng L, Shu S, Lin Z, 2021. Can cross entropy loss be robust to label noise? In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, 2206-2212."},{"key":"e_1_3_2_1_12_1","volume-title":"Optimizing loss functions through multivariate taylor polynomial parameterization. arXiv:2002.00059","author":"Santiago Gonzalez 0.","year":"2020","unstructured":"Santiago Gonzalez and Risto Miikkulainen. 202 0. Optimizing loss functions through multivariate taylor polynomial parameterization. arXiv:2002.00059 , 2020 b. Retrieved from https:\/\/arxiv.org\/abs\/2002.00059 Santiago Gonzalez and Risto Miikkulainen. 2020. Optimizing loss functions through multivariate taylor polynomial parameterization. arXiv:2002.00059, 2020b. Retrieved from https:\/\/arxiv.org\/abs\/2002.00059"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.52810\/TPRIS.2021.100019"},{"key":"e_1_3_2_1_14_1","unstructured":"Gonzalez S Miikkulainen R. 2020. Evolving loss functions with multivariate taylor polynomial parameterizations. arXiv:2002.00059. Retrieved from https:\/\/arxiv.org\/abs\/2002.00059v2  Gonzalez S Miikkulainen R. 2020. Evolving loss functions with multivariate taylor polynomial parameterizations. arXiv:2002.00059. Retrieved from https:\/\/arxiv.org\/abs\/2002.00059v2"},{"key":"e_1_3_2_1_15_1","first-page":"898","article-title":"Noninteractive locally private learning of linear models via polynomial approximations. Algorithmic Learning Theory","author":"Wang D","year":"2019","unstructured":"Wang D , Smith A , Xu J. 2019 . Noninteractive locally private learning of linear models via polynomial approximations. Algorithmic Learning Theory . PMLR , 898 - 903 . Wang D, Smith A, Xu J. 2019. Noninteractive locally private learning of linear models via polynomial approximations. Algorithmic Learning Theory. PMLR, 898-903.","journal-title":"PMLR"},{"key":"e_1_3_2_1_16_1","unstructured":"Leng Z Tan M Liu C 2022. PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions. arXiv:2204.12511. Retrieved from https:\/\/arxiv.org\/abs\/2204.12511  Leng Z Tan M Liu C 2022. PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions. arXiv:2204.12511. Retrieved from https:\/\/arxiv.org\/abs\/2204.12511"}],"event":{"name":"ICCIR 2022: 2022 2nd International Conference on Control and Intelligent Robot","acronym":"ICCIR 2022","location":"Nanjing China"},"container-title":["Proceedings of the 2022 2nd International Conference on Control and Intelligent Robotics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3548608.3559206","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3548608.3559206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:10:21Z","timestamp":1750183821000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3548608.3559206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,24]]},"references-count":17,"alternative-id":["10.1145\/3548608.3559206","10.1145\/3548608"],"URL":"https:\/\/doi.org\/10.1145\/3548608.3559206","relation":{},"subject":[],"published":{"date-parts":[[2022,6,24]]},"assertion":[{"value":"2022-10-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}