{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:50:03Z","timestamp":1770335403008,"version":"3.49.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2018AAA0102000"],"award-info":[{"award-number":["2018AAA0102000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236008"],"award-info":[{"award-number":["62236008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2051"],"award-info":[{"award-number":["U23B2051"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61931008"],"award-info":[{"award-number":["61931008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122075"],"award-info":[{"award-number":["62122075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976202"],"award-info":[{"award-number":["61976202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of Chinese Academy of Sciences","award":["XDB28000000"],"award-info":[{"award-number":["XDB28000000"]}]},{"name":"Innovation Funding of ICT, CAS","award":["E000000"],"award-info":[{"award-number":["E000000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/tpami.2024.3361861","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T18:37:45Z","timestamp":1707158265000},"page":"5062-5079","source":"Crossref","is-referenced-by-count":12,"title":["Algorithm-Dependent Generalization of AUPRC Optimization: Theory and Algorithm"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8881-3609","authenticated-orcid":false,"given":"Peisong","family":"Wen","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3512-7277","authenticated-orcid":false,"given":"Qianqian","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4409-4999","authenticated-orcid":false,"given":"Zhiyong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6885-1341","authenticated-orcid":false,"given":"Yuan","family":"He","sequence":"additional","affiliation":[{"name":"Security Department, Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15726-9"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350915"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3141095"},{"key":"ref5","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/1350486022000015850"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/8996.003.0015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780199535255.001.0001"},{"key":"ref9","first-page":"499","article-title":"Stability and generalization","volume":"2","author":"Bousquet","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_29"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_39"},{"key":"ref12","first-page":"193","article-title":"Learning to rank with nonsmooth cost functions","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Burges"},{"issue":"23\u2013581","key":"ref13","article-title":"From RankNet to LambdaRank to LambdaMART: An overview","volume":"11","author":"Burges","year":"2010","journal-title":"Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00196"},{"key":"ref15","first-page":"1565","article-title":"Learning imbalanced datasets with label-distribution-aware margin loss","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref17","first-page":"745","article-title":"Stability and generalization of learning algorithms that converge to global optima","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Charles"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00526"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991457"},{"key":"ref20","first-page":"315","article-title":"Ranking measures and loss functions in learning to rank","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref21","first-page":"370","article-title":"Two-layer generalization analysis for ranking using rademacher average","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref22","first-page":"1","article-title":"On the convergence of a class of adam-type algorithms for non-convex optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref23","article-title":"Stability and convergence trade-off of iterative optimization algorithms","author":"Chen","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553398"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143874"},{"issue":"1","key":"ref27","first-page":"55","article-title":"Stability of randomized learning algorithms","volume":"6","author":"Elisseeff","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01105"},{"key":"ref29","first-page":"6726","article-title":"Hypothesis set stability and generalization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Foster"},{"key":"ref30","first-page":"8759","article-title":"Uniform convergence of gradients for non-convex learning and optimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Foster"},{"key":"ref31","first-page":"939","article-title":"On the consistency of AUC pairwise optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gao"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-8958-3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref34","first-page":"1225","article-title":"Train faster, generalize better: Stability of stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hardt"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00423"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref37","first-page":"198","article-title":"End-to-end training of object class detectors for mean average precision","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Henderson"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref39","first-page":"4784","article-title":"Optimizing black-box metrics with adaptive surrogates","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46128-1_50"},{"key":"ref41","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.118.008678"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553449"},{"key":"ref44","first-page":"21236","article-title":"Sharper generalization bounds for pairwise learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref45","first-page":"21216","article-title":"Generalization guarantee of SGD for pairwise learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lei"},{"key":"ref46","first-page":"6175","article-title":"Stability and generalization of stochastic gradient methods for minimax problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lei"},{"key":"ref47","first-page":"5809","article-title":"Fine-grained analysis of stability and generalization for stochastic gradient descent","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lei"},{"key":"ref48","first-page":"1","article-title":"On generalization error bounds of noisy gradient methods for non-convex learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20042"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.009"},{"key":"ref52","first-page":"13669","article-title":"Benefits of overparameterized convolutional residual networks: Function approximation under smoothness constraint","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.238"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00062-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076115"},{"key":"ref56","first-page":"2312","article-title":"Efficient optimization for average precision SVM","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Mohapatra"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00389"},{"key":"ref58","first-page":"605","article-title":"Generalization bounds of SGLD for non-convex learning: Two theoretical viewpoints","volume-title":"Proc. Conf. Learn. Theory","author":"Mou"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref60","article-title":"A ranking-based, balanced loss function unifying classification and localisation in object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Oksuz"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.02.010"},{"key":"ref62","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref63","first-page":"1","article-title":"Differentiation of blackbox combinatorial solvers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pogan\u010di\u0107"},{"issue":"1","key":"ref64","first-page":"1","article-title":"On the mathematical foundations of learning","volume":"39","author":"Poggio","year":"2002","journal-title":"Amer. Math. Soc."},{"key":"ref65","first-page":"1752","article-title":"Stochastic optimization of areas under precision-recall curves with provable convergence","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9124-x"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2007.07.016"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/65943.65945"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00521"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344196"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref72","first-page":"2635","article-title":"Learnability, stability and uniform convergence","volume":"11","author":"Shalev-Shwartz","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"ref74","first-page":"2169","article-title":"Training deep neural networks via direct loss minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref75","first-page":"315","article-title":"Generalization error bounds for learning to rank: Does the length of document lists matter?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tewari"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331337"},{"key":"ref77","first-page":"4170","article-title":"Learning deep embeddings with histogram loss","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ustinova"},{"key":"ref78","article-title":"A data-dependent generalisation error bound for the AUC","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Usunier"},{"key":"ref79","first-page":"1369","article-title":"Generalization error bounds for classifiers trained with interdependent data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Usunier"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref82","first-page":"23292","article-title":"Finite-sum coupled compositional stochastic optimization: Theory and applications","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref83","first-page":"3753","article-title":"Momentum accelerates the convergence of stochastic AUPRC maximization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Wang"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00516"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00642"},{"key":"ref87","first-page":"5025","article-title":"When false positive is intolerant: End-to-end optimization with low FPR for multipartite ranking","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref88","first-page":"28335","article-title":"Exploring the algorithm-dependent generalization of AUPRC optimization with list stability","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390306"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3554729"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3101125"},{"key":"ref92","first-page":"1","article-title":"Compositional training for end-to-end deep AUC maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/1277741.1277790"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref95","first-page":"2053","article-title":"An improved analysis of training over-parameterized deep neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zou"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10550108\/10422838.pdf?arnumber=10422838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:09:17Z","timestamp":1725995357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10422838\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":95,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3361861","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":[[2024,7]]}}}