{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:28:25Z","timestamp":1774024105612,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/ciss48834.2020.1570627167","type":"proceedings-article","created":{"date-parts":[[2020,5,8]],"date-time":"2020-05-08T02:27:40Z","timestamp":1588904860000},"page":"1-5","source":"Crossref","is-referenced-by-count":27,"title":["Exploring the Role of Loss Functions in Multiclass Classification"],"prefix":"10.1109","author":[{"given":"Ahmet","family":"Demirkaya","sequence":"first","affiliation":[]},{"given":"Jiasi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Samet","family":"Oymak","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"1611","article-title":"Does data interpolation contradict statistical optimality?","author":"belkin","year":"2019","journal-title":"The 22nd International Conference on Artificial Intelligence and Statistics AISTATS 2019"},{"key":"ref11","article-title":"Generalization guarantees for neural networks via harnessing the lowrank structure of the jacobian","author":"oymak","year":"2019"},{"key":"ref12","article-title":"Overfitting or perfect fitting? risk bounds for classification and regression rules that interpolate","author":"belkin","year":"2018"},{"key":"ref13","first-page":"185","article-title":"On the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function","volume":"181","author":"dunne","year":"1997","journal-title":"Proc 8th Aust Conf on the Neural Networks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-005-0467-y"},{"key":"ref15","first-page":"1756","article-title":"Cross-entropy vs. squared error training: a theoretical and experimental comparison","volume":"13","author":"golik","year":"2013","journal-title":"InterSpeech"},{"key":"ref16","article-title":"Visualising basins of attraction for the cross-entropy and the squared error neural network loss functions","volume":"abs 1901 2302","author":"bosman","year":"2019","journal-title":"CoRR"},{"key":"ref17","article-title":"Extreme multi class classification","author":"choromanska","year":"2013","journal-title":"NIPS Workshop eXtreme Classification"},{"key":"ref18","first-page":"3069","article-title":"Pd-sparse: A primal and dual sparse approach to extreme multiclass and multilabel classification","author":"yen","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"13834","article-title":"Sampled softmax with random fourier features","volume":"32","author":"rawat","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref4","author":"papoulis","year":"2002","journal-title":"Probability random variables and stochastic processes"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794308.006"},{"key":"ref3","first-page":"1007","article-title":"On the consistency of multiclass classification methods","volume":"8","author":"tewari","year":"2007","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref29","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref5","volume":"247","author":"bourlard","year":"2012","journal-title":"Connectionist Speech Recognition A Hybrid Approach"},{"key":"ref8","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(91)90009-T"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.146"},{"key":"ref9","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume":"97","author":"du","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","article-title":"Gradient descent maximizes the margin of homogeneous neural networks","author":"lyu","year":"2019"},{"key":"ref22","article-title":"Squared earth mover’s distance-based loss for training deep neural networks","author":"hou","year":"2016"},{"key":"ref21","first-page":"1772","article-title":"The implicit bias of gradient descent on nonseparable data","author":"ji","year":"2019","journal-title":"Conference on Learning Theory COLT 2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2018.00125"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68612-7_15"},{"key":"ref26","article-title":"Stochastic gradient descent optimizes over-parameterized deep relu networks","author":"zou","year":"2018"},{"key":"ref25","first-page":"4951","article-title":"Overparameterized nonlinear learning: Gradient descent takes the shortest path?","author":"oymak","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2020 54th Annual Conference on Information Sciences and Systems (CISS)","location":"Princeton, NJ, USA","start":{"date-parts":[[2020,3,18]]},"end":{"date-parts":[[2020,3,20]]}},"container-title":["2020 54th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9081570\/9086165\/09086269.pdf?arnumber=9086269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T15:46:29Z","timestamp":1656344789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9086269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/ciss48834.2020.1570627167","relation":{},"subject":[],"published":{"date-parts":[[2020,3]]}}}