{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T01:06:35Z","timestamp":1777338395702,"version":"3.51.4"},"reference-count":60,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302305"],"award-info":[{"award-number":["62302305"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Sailing Program","award":["22YF1428500"],"award-info":[{"award-number":["22YF1428500"]}]},{"name":"Core Facility Platform of Computer Science and Communication, SIST, ShanghaiTech University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/ton.2025.3550732","type":"journal-article","created":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T13:02:11Z","timestamp":1746536531000},"page":"1840-1853","source":"Crossref","is-referenced-by-count":1,"title":["Safe Learning in Stochastic Continuum-Armed Bandit With Constraints and Its Application to Network Resource Management"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0704-271X","authenticated-orcid":false,"given":"Hengquan","family":"Guo","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1333","article-title":"Rectified pessimistic-optimistic learning for stochastic continuum-armed bandit with constraints","volume-title":"Proc. Learn. Dyn. Control Conf.","author":"Guo"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3466772.3467031"},{"key":"ref3","first-page":"1","article-title":"Contextual Gaussian process bandit optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Krause"},{"key":"ref4","first-page":"67","article-title":"Contextual bandits for adapting treatment in a mouse model of de novo carcinogenesis","volume-title":"Proc. 3rd Mach. Learn. Healthcare Conf.","volume":"85","author":"Durand"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17233"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/isit45174.2021.9518176"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06019-1"},{"key":"ref8","first-page":"997","article-title":"Safe exploration for optimization with Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sui"},{"key":"ref9","first-page":"4781","article-title":"Stagewise safe Bayesian optimization with Gaussian processes","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sui"},{"issue":"123","key":"ref10","first-page":"1","article-title":"ADMMBO: Bayesian optimization with unknown constraints using ADMM","volume":"20","author":"Ariafar","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","first-page":"8370","article-title":"A Bayesian approach for stochastic continuum-armed bandit with long-term constraints","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Shi"},{"key":"ref12","first-page":"14","article-title":"On kernelized multi-armed bandits with constraints","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref13","first-page":"1015","article-title":"Gaussian process optimization in the bandit setting: No regret and experimental design","volume-title":"Proc. 27th Int. Conf. Int. Conf. Mach. Learn.","author":"Srinivas"},{"key":"ref14","first-page":"844","article-title":"On kernelized multi-armed bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chowdhury"},{"key":"ref15","first-page":"38485","article-title":"Constrained efficient global optimization of expensive black-box functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref16","first-page":"22145","article-title":"Bayesian optimization under stochastic delayed feedback","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.23919\/WiOpt56218.2022.9930591"},{"key":"ref18","first-page":"3458","article-title":"Linear contextual bandits with knapsacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Agrawal"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3164539"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3557045"},{"key":"ref21","first-page":"4633","article-title":"Contextual bandits with packing and covering constraints: A modular Lagrangian approach via regression","volume-title":"Proc. Annu. Conf. Comput. Learn. Theory","author":"Slivkins"},{"key":"ref22","first-page":"2204","article-title":"Stochastic constrained contextual bandits via Lyapunov optimization based estimation to decision framework","volume-title":"Proc. 37th Annu. Conf. Learn. Theory","author":"Guo"},{"key":"ref23","first-page":"1","article-title":"On stochastic contextual bandits with knapsacks in small budget regime","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.07.558"},{"issue":"1","key":"ref25","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":"ref26","first-page":"3280","article-title":"Safety-aware algorithms for adversarial contextual bandit","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref27","article-title":"Online convex optimization with time-varying constraints","author":"Neely","year":"2017","journal-title":"arXiv:1702.04783"},{"key":"ref28","first-page":"1","article-title":"Cautious regret minimization: Online optimization with long-term budget constraints","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Liakopoulos"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2996178"},{"key":"ref30","first-page":"14712","article-title":"A single recipe for online submodular maximization with adversarial or stochastic constraints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sadeghi"},{"key":"ref31","first-page":"6149","article-title":"Online convex optimization for cumulative constraints","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Yuan"},{"key":"ref32","first-page":"11998","article-title":"Regret and cumulative constraint violation analysis for online convex optimization with long term constraints","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yi"},{"key":"ref33","article-title":"Regret and cumulative constraint violation analysis for distributed online constrained convex optimization","author":"Yi","year":"2021","journal-title":"arXiv:2105.00321"},{"key":"ref34","first-page":"36439","article-title":"Online convex optimization with hard constraints: Towards the best of two worlds and beyond","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Guo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2839563"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2021.3066142"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00031"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2023.102376"},{"key":"ref41","article-title":"A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","author":"Brochu","year":"2010","journal-title":"arXiv:1012.2599"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3545611"},{"key":"ref44","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Snoek"},{"key":"ref45","first-page":"55","article-title":"Surrogating the surrogate: Accelerating Gaussian-process-based global optimization with a mixture cross-entropy algorithm","volume-title":"Proc. 27th Int. Conf. Mach. Learn. (ICML)","author":"Bardenet"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/BF00941892"},{"key":"ref47","first-page":"654","article-title":"Finite-time analysis of kernelised contextual bandits","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Va\u0142ko"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1017\/9781108571401"},{"key":"ref49","first-page":"9712","article-title":"Linear bandits with stochastic delayed feedback","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Vernade"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2013.2277869"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CISS50987.2021.9400292"},{"key":"ref52","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","volume-title":"Proc. 20th Int. Conf. Mach. Learn.","author":"Zinkevich"},{"key":"ref53","first-page":"579","article-title":"Dynamical models and tracking regret in online convex programming","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Hall"},{"key":"ref54","first-page":"1330","article-title":"Adaptive online learning in dynamic environments","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3261050"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2021.4024"},{"key":"ref57","first-page":"746","article-title":"A simple approach for non-stationary linear bandits","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","volume":"108","author":"Zhao"},{"key":"ref58","first-page":"16522","article-title":"Non-stationary bandits with knapsacks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref59","first-page":"4300","article-title":"Non-stationary reinforcement learning without prior knowledge: An optimal black-box approach","volume-title":"Proc. 34th Conf. Learn. Theory","author":"Wei"},{"key":"ref60","volume-title":"New York ISO Open Access Pricing Data","year":"2022"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11131549\/10988611.pdf?arnumber=10988611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:07Z","timestamp":1755910327000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10988611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":60,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/ton.2025.3550732","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}