{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:23:09Z","timestamp":1775229789058,"version":"3.50.1"},"reference-count":210,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tpami.2023.3296062","type":"journal-article","created":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:40:30Z","timestamp":1689615630000},"page":"1-20","source":"Crossref","is-referenced-by-count":22,"title":["Rank-based Decomposable Losses in Machine Learning: A Survey"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1446-4140","authenticated-orcid":false,"given":"Shu","family":"Hu","sequence":"first","affiliation":[{"name":"Heinz College of Information Systems and Public Policy, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7528-2407","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, SUNY, Buffalo, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0992-685X","authenticated-orcid":false,"given":"Siwei","family":"Lyu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University at Buffalo, SUNY, Buffalo, NY, USA"}]}],"member":"263","reference":[{"key":"ref57","article-title":"The elements of statistical learning: data mining, inference, and prediction","volume":"2","author":"hastie","year":"2009"},{"key":"ref207","first-page":"2525","article-title":"Not all samples are created equal: Deep learning with importance sampling","author":"katharopoulos","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-004-0155-9"},{"key":"ref208","first-page":"7276","article-title":"Training deep models faster with robust, approximate importance sampling","author":"johnson","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2371656.2371658"},{"key":"ref205","author":"mohri","year":"2018","journal-title":"Foundations of Machine Learning"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref206","article-title":"Biased importance sampling for deep neural network training","author":"katharopoulos","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1198\/016214505000000907"},{"key":"ref203","article-title":"Probabilistic machine learning: Advanced topics","author":"murphy","year":"2023"},{"key":"ref52","volume":"479","author":"minsky","year":"1969","journal-title":"An Introduction to Computational Geometry"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1233901"},{"key":"ref201","first-page":"1007","article-title":"On the consistency of multiclass classification methods","volume":"8","author":"tewari","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-004-0134-1"},{"key":"ref202","first-page":"341","article-title":"On the consistency of multi-label learning","author":"gao","year":"2011","journal-title":"Proc 35th Annu Conf Learn Theory"},{"key":"ref209","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","author":"paul","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref210","first-page":"6957","article-title":"Learning deep neural networks under agnostic corrupted supervision","author":"liu","year":"2021","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref51","first-page":"615","article-title":"On convergence proofs for perceptrons","volume":"12","author":"novikoff","year":"1962","journal-title":"Proc Symp Math Theory Automata"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1037\/h0042519"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/0169-7439(87)80084-9"},{"key":"ref45","first-page":"793","article-title":"Minimizing the maximal loss: How and why","author":"shalev-shwartz","year":"2016","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719062"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3130348.3130374"},{"key":"ref41","article-title":"Maximizing AUC with deep learning for classification of imbalanced mammogram datasets","author":"sulam","year":"2017","journal-title":"Proc Eurograph Workshop Vis Comput Biol Med"},{"key":"ref44","first-page":"1025","article-title":"A family of additive online algorithms for category ranking","volume":"3","author":"crammer","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00764"},{"key":"ref49","article-title":"Designing off-sample performance metrics","author":"holland","year":"2021"},{"key":"ref8","article-title":"Learning with average top-k loss","author":"fan","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","article-title":"Introductory real analysis","author":"kolmogorov","year":"1975","journal-title":"Courier Corporation"},{"key":"ref9","first-page":"5739","article-title":"Learning with bad training data via iterative trimmed loss minimization","author":"shen","year":"2019","journal-title":"Proc Int Conf Mach Learn Appl"},{"key":"ref4","volume":"463","author":"baeza-yates","year":"1999","journal-title":"Modern Information Retrieval"},{"key":"ref3","first-page":"848","article-title":"Optimizing classifier performance via an approximation to the Wilcoxon-Mann-Whitney statistic","author":"yan","year":"2003","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref6","first-page":"265","article-title":"On the algorithmic implementation of multiclass kernel-based vector machines","volume":"2","author":"crammer","year":"2001","journal-title":"J Mach Learn Res"},{"key":"ref5","author":"murphy","year":"2022","journal-title":"Probabilistic Machine Learning An introduction"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.01.104"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3390\/s19204401"},{"key":"ref40","first-page":"906","article-title":"One-pass AUC optimization","author":"gao","year":"2013","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref35","article-title":"Learning to rank for information retrieval","volume":"3","author":"liu","year":"2009","journal-title":"Found Trends Inf Retrieval"},{"key":"ref34","first-page":"171","article-title":"Harmonic-mean COX models: A ruler for equal attention to risk","author":"wang","year":"2021","journal-title":"Proc Survival Prediction-Algorithms Challenges Appl"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1148\/radiology.143.1.7063747"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2953856"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"cortes","year":"1995","journal-title":"Mach Learn"},{"key":"ref30","author":"kleinbaum","year":"2002","journal-title":"Logistic Regression"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080828"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2003.11.019"},{"key":"ref39","article-title":"Online AUC maximization","author":"zhao","year":"2011"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1023\/A:1010920819831","article-title":"A simple generalisation of the area under the ROC curve for multiple class classification problems","volume":"45","author":"hand","year":"2001","journal-title":"Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.127"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CIBCB48159.2020.9277638"},{"key":"ref26","volume":"7","author":"li","year":"2014","journal-title":"Learning to Rank for Information Retrieval and Natural Language Processing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1587\/transinf.E94.D.1854"},{"key":"ref20","first-page":"633","article-title":"Rankmax: An adaptive projection alternative to the softmax function","author":"kong","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.32604\/jihpp.2021.016835"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3005393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4310\/CIS.2018.v18.n1.a2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3554729"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s40745-020-00253-5"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1079120130"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.07.005"},{"key":"ref129","article-title":"Minimizing close-k aggregate loss improves classification","author":"he","year":"2018"},{"key":"ref97","article-title":"When do curricula work?","author":"wu","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref126","article-title":"Support vector classification with positive homogeneous risk functionals","author":"tsyurmasto","year":"2013"},{"key":"ref96","first-page":"669","article-title":"Ordered SGD: A new stochastic optimization framework for empirical risk minimization","author":"kawaguchi","year":"2020","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3390\/e19020083"},{"key":"ref99","article-title":"On tilted losses in machine learning: Theory and applications","author":"li","year":"2021"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143870"},{"key":"ref98","article-title":"Tilted empirical risk minimization","author":"li","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref125","first-page":"536","article-title":"Robust support vector machine training via convex outlier ablation","author":"xu","year":"2006","journal-title":"Proc Conf Assoc Adv Artif Intell"},{"key":"ref93","first-page":"517","article-title":"A robust zero-sum game framework for pool-based active learning","author":"zhu","year":"2019","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1198\/jcgs.2010.09206"},{"key":"ref92","article-title":"Distributionally robust optimization: A review","author":"rahimian","year":"2019"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2013.39"},{"key":"ref95","first-page":"2188","article-title":"Distributionally robust optimization for deep kernel multiple instance learning","author":"sapkota","year":"2021","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008663629662"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_23"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1198\/016214504000000098"},{"key":"ref130","first-page":"219","article-title":"Support vector machines for multi-class pattern recognition","author":"weston","year":"1999","journal-title":"Proc Eur Symp Artif Neural Netw"},{"key":"ref91","article-title":"Efficient online-bandit strategies for minimax learning problems","author":"roux","year":"2021"},{"key":"ref90","first-page":"8847","article-title":"Large-scale methods for distributionally robust optimization","author":"levy","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390289"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7895"},{"key":"ref86","article-title":"Probabilistically robust learning: Balancing average-and worst-case performance","author":"robey","year":"2022"},{"key":"ref137","first-page":"1","article-title":"A unified view on multi-class support vector classification","volume":"17","author":"dogan","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976595"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5064-8"},{"key":"ref88","first-page":"179","article-title":"Extension of the nu-SVM range for classification","author":"p\u00e9rez-cruz","year":"2003","journal-title":"NATO Adv Study Inst Learn Theory Pract 2002"},{"key":"ref135","first-page":"1","article-title":"The truth of the F-measure","volume":"1","author":"sasaki","year":"2007","journal-title":"Teach Tutor Mater"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015565"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007649029923"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11228-021-00609-w"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref81","first-page":"13867","article-title":"Learning bounds for risk-sensitive learning","author":"lee","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref145","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11265-021-01716-5"},{"key":"ref142","article-title":"Delving into transferable adversarial examples and black-box attacks","author":"liu","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref83","article-title":"Spectral risk-based learning using unbounded losses","author":"holland","year":"2021"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref140","article-title":"Intriguing properties of neural networks","author":"szegedy","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref141","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref80","first-page":"1036","article-title":"Adaptive sampling for stochastic risk-averse learning","author":"curi","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref79","first-page":"6786","article-title":"Fairness risk measures","author":"williamson","year":"2019","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref108","first-page":"14638","article-title":"Top-k training of GANs: Improving GAN performance by throwing away bad samples","author":"sinha","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref78","article-title":"Robust imitation learning from corrupted demonstrations","author":"liu","year":"2022"},{"key":"ref109","volume":"523","author":"huber","year":"2004","journal-title":"Robust Statistics"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-64655-4"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9630310"},{"key":"ref75","first-page":"713","article-title":"Robust compressed sensing using generative models","author":"jalal","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.11.005"},{"key":"ref74","first-page":"543","article-title":"Loss minimization and parameter estimation with heavy tails","volume":"17","author":"hsu","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3004322"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.4171\/JEMS\/937"},{"key":"ref102","article-title":"Deep learning from shallow dives: Sonar image generation and training for underwater object detection","author":"lee","year":"2018"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1214\/19-AOS1828"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2019.12.299"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.3182\/20110828-6-IT-1002.03467"},{"key":"ref111","article-title":"No regret sample selection with noisy labels","author":"song","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-7821-5_15"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/340"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1214\/15-AOS1350"},{"key":"ref72","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1137\/1027074","article-title":"Problem complexity and method efficiency in optimization","volume":"27","author":"nemirovskij","year":"1985","journal-title":"SIAM Review"},{"key":"ref110","first-page":"2666","article-title":"Learning entangled single-sample distributions via iterative trimming","author":"yuan","year":"2020","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10958-022-05689-z"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1235-y"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s10958-021-05256-y"},{"key":"ref117","first-page":"14879","article-title":"Coresets via bilevel optimization for continual learning and streaming","volume":"33","author":"borsos","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.2307\/2288718"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2021.2248"},{"key":"ref64","article-title":"Robust optimization for non-convex objectives","volume":"30","author":"chen","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref115","first-page":"7524","article-title":"Robust unsupervised learning via l-statistic minimization","author":"maurer","year":"2021","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-39568-1"},{"key":"ref116","volume":"162","author":"serfling","year":"2009","journal-title":"Approximation Theorems of Mathematical Statistics"},{"key":"ref66","first-page":"4615","article-title":"Agnostic federated learning","author":"mohri","year":"2019","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref113","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume":"31","author":"han","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref65","first-page":"866","article-title":"Thinking inside the ball: Near-optimal minimization of the maximal loss","author":"carmon","year":"2021","journal-title":"Proc 34th Conf Learn Theory"},{"key":"ref114","article-title":"Robust statistics: A brief introduction and overview","volume":"94","author":"hampel","year":"2001","journal-title":"Res Rep"},{"key":"ref60","first-page":"1233","article-title":"Beating SGD: Learning SVMs in sublinear time","author":"hazan","year":"2011","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487674"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00958"},{"key":"ref62","first-page":"2216","article-title":"Stochastic gradient methods for distributionally robust optimization with f-divergences","author":"namkoong","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-0208(08)72402-2"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s101070100286"},{"key":"ref121","article-title":"Large-scale optimization of partial AUC in a range of false positive rates","author":"yao","year":"2022"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097991"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3083397"},{"key":"ref170","article-title":"A unified DRO view of multi-class loss functions with top-n consistency","author":"zhu","year":"2021","journal-title":"Proc Int Conf Neural Inf Process Syst Workshop"},{"key":"ref177","article-title":"Trade-offs in top-k classification accuracies on losses for deep learning","author":"sawada","year":"2020"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2969677"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00120"},{"key":"ref176","article-title":"Leveraging uncertainty to rethink loss functions and evaluation measures for egocentric action anticipation","author":"furnari","year":"2018","journal-title":"Proc Eur Conf Comput Vis Workshops"},{"key":"ref173","first-page":"1940","article-title":"Stochastic negative mining for learning with large output spaces","author":"reddi","year":"2019","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref174","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref171","first-page":"774","article-title":"Learning weighted top- support vector machine","author":"kato","year":"2019","journal-title":"Proc 11th Asian Conf Mach Learn"},{"key":"ref172","first-page":"432","article-title":"Frank-wolfe algorithm for learning SVM-typemulti-category classifiers","author":"tajima","year":"2021","journal-title":"Proc SIAM Int Conf Data Mining"},{"key":"ref179","article-title":"The limited multi-label projection layer","author":"amos","year":"2019"},{"key":"ref180","article-title":"Adversarial examples for extreme multilabel text classification","author":"qaraei","year":"2021"},{"key":"ref181","first-page":"1954","article-title":"Submodularity in data subset selection and active learning","author":"wei","year":"2015","journal-title":"Proc Int Conf Mach Learn Appl"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0190(02)00370-8"},{"key":"ref189","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref186","first-page":"12345","article-title":"DORO: Distributional and outlier robust optimization","author":"zhai","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref183","article-title":"Self-paced learning for latent variable models.","author":"kumar","year":"2010","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9206614"},{"key":"ref149","article-title":"Can domain knowledge alleviate adversarial attacks in multi-label classifiers?","author":"melacci","year":"2020"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.17"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00166"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1145\/3318299.3318335"},{"key":"ref156","first-page":"10727","article-title":"On the consistency of top-k surrogate losses","author":"yang","year":"2020","journal-title":"Proc IEEE Int Conf Mach Learn Appl"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10813"},{"key":"ref154","article-title":"Set-valued classification–overview via a unified framework","author":"chzhen","year":"2021"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.08.004"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2931352"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref159","first-page":"1567","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","author":"cao","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref157","article-title":"Stochastic smoothing of the top-k calibrated hinge loss for deep imbalanced classification","author":"garcin","year":"2022"},{"key":"ref158","first-page":"9508","article-title":"Learning with differentiable pertubed optimizers","author":"berthet","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref166","article-title":"Smooth loss functions for deep top-k classification","author":"berrada","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref167","article-title":"Doubly-stochastic mining for heterogeneous retrieval","author":"rawat","year":"2020"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2826039"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-004-0552-5"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00396"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553509"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.199"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00411"},{"key":"ref13","first-page":"21013","article-title":"Learning by minimizing the sum of ranked range","volume":"33","author":"hu","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref12","article-title":"Sample selection for fair and robust training","author":"roh","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00755"},{"key":"ref14","first-page":"1","article-title":"Sum of ranked range loss for supervised learning","volume":"23","author":"hu","year":"2022","journal-title":"J Mach Learn Res"},{"key":"ref11","article-title":"Choosing the sample with lowest loss makes SGD robust","author":"shah","year":"2020","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref10","article-title":"Iterative least trimmed squares for mixed linear regression","author":"shen","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.163"},{"key":"ref16","article-title":"Top-k multiclass SVM","author":"lapin","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","first-page":"1","article-title":"Learning with Fenchel-Young losses","volume":"21","author":"blondel","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2751607"},{"key":"ref2","author":"vapnik","year":"1999","journal-title":"The Nature of Statistical Learning Theory"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.168"},{"key":"ref191","first-page":"832","article-title":"Scalable learning of non-decomposable objectives","author":"eban","year":"2017","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref192","article-title":"Accuracy at the top","volume":"25","author":"boyd","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref190","first-page":"1205","article-title":"Efficient bregman projections onto the permutahedron and related polytopes","author":"lim","year":"2016","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref199","first-page":"9804","article-title":"Calibration and consistency of adversarial surrogate losses","volume":"34","author":"awasthi","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/1645953.1646033"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372165"},{"key":"ref195","first-page":"4260","article-title":"Optimization and analysis of the pap, k metric for recommender systems","author":"hiranandani","year":"2020","journal-title":"Proc Int Conf Mach Learn Appl"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-39940-9_488"},{"key":"ref193","article-title":"A univariate bound of area under ROC","author":"lyu","year":"2018","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/10184478.pdf?arnumber=10184478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T15:30:28Z","timestamp":1696433428000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10184478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":210,"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3296062","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}