{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:42:14Z","timestamp":1782834134029,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["22ZR1441700"],"award-info":[{"award-number":["22ZR1441700"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/ton.2025.3538709","type":"journal-article","created":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T13:46:39Z","timestamp":1740491199000},"page":"1543-1558","source":"Crossref","is-referenced-by-count":3,"title":["Neural Constrained Combinatorial Bandits"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0996-5380","authenticated-orcid":false,"given":"Shangshang","family":"Wang","sequence":"first","affiliation":[{"name":"Viterbi School of Engineering, University of Southern California (USC), Los Angeles, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simeng","family":"Bian","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5869-3186","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-1391","authenticated-orcid":false,"given":"Ziyu","family":"Shao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10228958"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9693.001.0001"},{"key":"ref5","first-page":"151","article-title":"Combinatorial multi-armed bandit: General framework and applications","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"issue":"3","key":"ref7","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","volume-title":"Proc. NeurIPS","volume":"24","author":"Abbasi-Yadkori"},{"key":"ref9","first-page":"1","article-title":"Birds of a feather help: Context-aware client selection for federated learning","volume-title":"Proc. FL-AAAI","author":"Cao"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3465456.3467546"},{"key":"ref11","first-page":"1","article-title":"Finite-time analysis of kernelised contextual bandits","volume-title":"Proc. UAI","author":"Valko"},{"key":"ref12","first-page":"1","article-title":"Neural contextual bandits with UCB-based exploration","volume-title":"Proc. ICML","author":"Zhou"},{"key":"ref13","first-page":"1","article-title":"Neural Thompson sampling","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref14","first-page":"1","article-title":"Offline neural contextual bandits: Pessimism, optimization and generalization","volume-title":"Proc. ICLR","author":"Nguyen-Tang"},{"key":"ref15","first-page":"1","article-title":"EE-net: Exploitation-exploration neural networks in contextual bandits","volume-title":"Proc. ICLR","author":"Ban"},{"key":"ref16","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3508396.3512886"},{"key":"ref18","article-title":"Provably and practically efficient neural contextual bandits","author":"Salgia","year":"2022","journal-title":"arXiv:2206.00099"},{"key":"ref19","article-title":"On kernelized multi-armed bandits with constraints","author":"Zhou","year":"2022","journal-title":"arXiv:2203.15589"},{"key":"ref20","first-page":"1","article-title":"An efficient pessimistic-optimistic algorithm for stochastic linear bandits with general constraints","volume-title":"Proc. NeurIPS","author":"Liu"},{"key":"ref21","first-page":"1","article-title":"Resourceful contextual bandits","volume-title":"Proc. COLT","author":"Badanidiyuru"},{"key":"ref22","first-page":"3450","article-title":"Linear contextual bandits with knapsacks","volume-title":"Proc. NeurIPS","volume":"29","author":"Agrawal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796683"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3173792"},{"key":"ref25","article-title":"POND: Pessimistic-optimistic oNline dispatching","author":"Liu","year":"2020","journal-title":"arXiv:2010.09995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737461"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3072115"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM48099.2022.10000778"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10278850"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5986"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2796314.2745847"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3164539"},{"key":"ref33","first-page":"1","article-title":"Budget-constrained bandits over general cost and reward distributions","volume-title":"Proc. AISTATS","author":"\u00c7ayci"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2014.2316517"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2016.7524432"},{"key":"ref36","first-page":"1","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. NeurIPS","author":"Jacot"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79995-2"},{"issue":"95","key":"ref38","first-page":"2651","article-title":"Universal kernels","volume":"7","author":"Micchelli","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","first-page":"8139","article-title":"On exact computation with an infinitely wide neural net","volume-title":"Proc. NeurIPS","volume":"32","author":"Arora"},{"key":"ref40","first-page":"10835","article-title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks","volume-title":"Proc. NeurIPS","volume":"32","author":"Cao"},{"key":"ref41","first-page":"9252","article-title":"Linear stochastic bandits under safety constraints","volume-title":"Proc. NeurIPS","volume":"32","author":"Amani"},{"key":"ref42","article-title":"Safe linear Thompson sampling with side information","author":"Moradipari","year":"2019","journal-title":"arXiv:1911.02156"},{"key":"ref43","first-page":"1","article-title":"Fair contextual multi-armed bandits: Theory and experiments","volume-title":"Proc. UAI","author":"Chen"},{"key":"ref44","first-page":"1","article-title":"When do neural networks outperform kernel methods","volume-title":"Proc. NeurIPS","author":"Ghorbani"},{"key":"ref45","article-title":"Online learning with corrupted context: Corrupted contextual bandits","author":"Bouneffouf","year":"2020","journal-title":"arXiv:2006.15194"},{"key":"ref46","article-title":"Regularization for deep learning: A taxonomy","author":"Kuka\u010dka","year":"2017","journal-title":"arXiv:1710.10686"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"issue":"1","key":"ref48","first-page":"2503","article-title":"Trading regret for efficiency: Online convex optimization with long term constraints","volume":"13","author":"Mahdavi","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","first-page":"402","article-title":"Adaptive algorithms for online convex optimization with long-term constraints","volume-title":"Proc. ICML","author":"Jenatton"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1017\/9781108231596"},{"key":"ref51","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","volume-title":"Proc. ICML","author":"Srinivas"},{"key":"ref52","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref53","first-page":"1","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. NeurIPS","author":"Kumar"},{"key":"ref54","first-page":"1","article-title":"Online convex optimization with hard constraints: Towards the best of two worlds and beyond","volume-title":"Proc. NeurIPS","author":"Guo"},{"key":"ref55","doi-asserted-by":"crossref","DOI":"10.1109\/TON.2025.3538709","article-title":"Neural constrained combinatorial bandits","author":"Wang","year":"2025"},{"key":"ref56","first-page":"586","article-title":"Parametric bandits: The generalized linear case","volume-title":"Proc. NeurIPS","volume":"23","author":"Filippi"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2449323"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809682"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1511.08458"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020579"},{"key":"ref63","article-title":"Convolutional neural bandit for visual-aware recommendation","author":"Ban","year":"2021","journal-title":"arXiv:2107.07438"},{"key":"ref64","first-page":"1","article-title":"From bandits to experts: On the value of side-observations","volume-title":"Proc. NeurIPS","author":"Mannor"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2011.12.028"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11131549\/10902634.pdf?arnumber=10902634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:05Z","timestamp":1755910325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":65,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3538709","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}