{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:00:49Z","timestamp":1775815249405,"version":"3.50.1"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,2]],"date-time":"2022-05-02T00:00:00Z","timestamp":1651449600000},"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":[],"published-print":{"date-parts":[[2022,5,2]]},"DOI":"10.1109\/infocom48880.2022.9796701","type":"proceedings-article","created":{"date-parts":[[2022,6,20]],"date-time":"2022-06-20T21:18:49Z","timestamp":1655759929000},"page":"2078-2087","source":"Crossref","is-referenced-by-count":15,"title":["Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach"],"prefix":"10.1109","author":[{"given":"Shuzhao","family":"Xie","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School"}]},{"given":"Yuan","family":"Xue","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School"}]},{"given":"Yifei","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,UM-SJTU Joint Institute"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"0","journal-title":"ICML"},{"key":"ref11","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"ICMLC 2018"},{"key":"ref12","first-page":"2688","article-title":"Ensemble methods for object detection","author":"casado-garcia","year":"0","journal-title":"ECAI 2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.685"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref15","article-title":"Weighted boxes fusion: Ensembling boxes for object detection models","author":"solovyev","year":"2019","journal-title":"arXiv preprint arXiv 1910 13038"},{"key":"ref16","article-title":"Spinning Up in Deep Reinforcement Learning","author":"achiam","year":"2018"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref18","article-title":"Alibaba cloud object detection","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3131365.3131372"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1153"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref27","article-title":"Deep reinforcement learning in large discrete action spaces","author":"dulac-arnold","year":"2015","journal-title":"arXiv preprint arXiv 1512 00327"},{"key":"ref3","article-title":"Inferbench: Understanding deep learning inference serving with an automatic benchmarking system","author":"zhang","year":"2020","journal-title":"arXiv preprint arXiv 2011 00177"},{"key":"ref6","article-title":"Azure computer vision","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362276"},{"key":"ref5","article-title":"Amazon rekognition","year":"2021"},{"key":"ref8","article-title":"Average precision","year":"2021"},{"key":"ref7","article-title":"Google vision ai","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00045"},{"key":"ref9","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"0","journal-title":"ECCV 2014"},{"key":"ref1","article-title":"Machine learning as a service (mlaas) market - growth, trends, covid-19 impact, and forecasts (2021 - 2026)","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.14778\/3231751.3231770"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2015.08.031"},{"key":"ref21","first-page":"32","article-title":"Cloud federation","volume":"2011","author":"kurze","year":"2011","journal-title":"Cloud Computing"},{"key":"ref24","first-page":"3566","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","author":"zahavy","year":"0","journal-title":"NeurIPS 2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1189"},{"key":"ref26","article-title":"Challenges of real-world reinforcement learning","author":"dulac-arnold","year":"2019","journal-title":"arXiv preprint arXiv 1904 12848"},{"key":"ref25","article-title":"Reinforcement learning with combinatorial actions: An application to vehicle routing","author":"delarue","year":"2020","journal-title":"NeurIPS"}],"event":{"name":"IEEE INFOCOM 2022 - IEEE Conference on Computer Communications","location":"London, United Kingdom","start":{"date-parts":[[2022,5,2]]},"end":{"date-parts":[[2022,5,5]]}},"container-title":["IEEE INFOCOM 2022 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9796607\/9796652\/09796701.pdf?arnumber=9796701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T20:01:02Z","timestamp":1657569662000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9796701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,2]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/infocom48880.2022.9796701","relation":{},"subject":[],"published":{"date-parts":[[2022,5,2]]}}}