{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T19:47:08Z","timestamp":1793476028295,"version":"4.5.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62202055"],"award-info":[{"award-number":["62202055"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515012843"],"award-info":[{"award-number":["2025A1515012843"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Start-up Fund from Beijing Normal University","award":["312200502510"],"award-info":[{"award-number":["312200502510"]}]},{"name":"Internal Fund from Beijing Normal-Hong Kong Baptist University","award":["UICR0400003-24"],"award-info":[{"award-number":["UICR0400003-24"]}]},{"name":"Internal Fund from Beijing Normal-Hong Kong Baptist University","award":["UICR0200022-25"],"award-info":[{"award-number":["UICR0200022-25"]}]},{"name":"Interdisciplinary Intelligence SuperComputer Center of Beijing Normal University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tsc.2025.3611379","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:46:35Z","timestamp":1758217595000},"page":"3567-3580","source":"Crossref","is-referenced-by-count":11,"title":["Cloud-Edge System for Scheduling Unpredictable LLM Requests With Combinatorial Bandit"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5996-2172","authenticated-orcid":false,"given":"Yandi","family":"Li","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University, Kowloon Tong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0994-3297","authenticated-orcid":false,"given":"Jianxiong","family":"Guo","sequence":"additional","affiliation":[{"name":"Advanced Institute of Natural Sciences, Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9375-4818","authenticated-orcid":false,"given":"Zhiqing","family":"Tang","sequence":"additional","affiliation":[{"name":"Advanced Institute of Natural Sciences, Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8866-4941","authenticated-orcid":false,"given":"Xingjian","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Computing, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-8382","authenticated-orcid":false,"given":"Juncheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4819-621X","authenticated-orcid":false,"given":"Tian","family":"Wang","sequence":"additional","affiliation":[{"name":"Advanced Institute of Natural Sciences, Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3937","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Advanced Institute of Natural Sciences, Beijing Normal University, Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3106401"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2922285"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3018159"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3064225"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3219261"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS62655.2024.00105"},{"key":"ref9","first-page":"613","article-title":"Clipper: A low-latency online prediction serving system","volume-title":"Proc. 14th USENIX Symp. Netw. Syst. Des. Implementation","author":"Crankshaw"},{"key":"ref10","first-page":"443","article-title":"Serving $\\lbrace${DNNs$\\rbrace$} like clockwork: Performance predictability from the bottom up","volume-title":"Proc. 14th USENIX Symp. Operating Syst. Des. Implementation","author":"Gujarati"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3139689"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.53"},{"key":"ref13","first-page":"1245","article-title":"Contextual combinatorial cascading bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2001.990693"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3362237"},{"key":"ref17","first-page":"521","article-title":"Orca: A distributed serving system for transformer-based generative models","volume-title":"Proc. 16th USENIX Symp. Operating Syst. Des. Implementation","author":"Yu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref19","article-title":"Fast distributed inference serving for large language models","author":"Wu","year":"2023"},{"key":"ref20","article-title":"Efficient interactive llm serving with proxy model-based sequence length prediction","author":"Qiu","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3402169"},{"key":"ref22","article-title":"Edge-cloud collaborative computing on distributed intelligence and model optimization: A survey","author":"Liu","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-024-00658-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.003.2400046"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3415661"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tcad.2025.3560221"},{"key":"ref27","first-page":"1659","article-title":"Combinatorial multi-armed bandit with general reward functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737654"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2021.3058685"},{"key":"ref30","first-page":"11492","article-title":"Neural contextual bandits with UCB-based exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref31","first-page":"14203","article-title":"Combinatorial neural bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hwang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref33","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref34","article-title":"Generalization bounds of stochastic gradient descent for wide and deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref35","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":"ref36","article-title":"Contextual bandits in imperfect environments: Analysis and applications","author":"Yang","year":"2021"},{"key":"ref37","first-page":"2312","article-title":"Improved algorithms for linear stochastic bandits","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Abbasi-Yadkori"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3182728"},{"key":"ref39","article-title":"Stanford alpaca: An instruction-following LLaMA model","author":"Taori","year":"2023","journal-title":"GitHub Repository"},{"key":"ref40","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref41","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref42","first-page":"46595","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref43","first-page":"1113","article-title":"Efficient learning in large-scale combinatorial semi-bandits","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wen"},{"key":"ref44","article-title":"Qwen2 technical report","author":"Team","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316534298"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.33086\/atcsj.v5i2.3743"},{"key":"ref47","volume-title":"Operating System Concepts","author":"Silberschatz","year":"1991"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.04.007"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11298270\/11169423.pdf?arnumber=11169423","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T12:25:55Z","timestamp":1766060755000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11169423\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2025.3611379","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"value":"1939-1374","type":"electronic"},{"value":"2372-0204","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}