{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T13:57:53Z","timestamp":1730296673869,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T00:00:00Z","timestamp":1716854400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,28]],"date-time":"2024-05-28T00:00:00Z","timestamp":1716854400000},"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":[[2024,5,28]]},"DOI":"10.1109\/smartnets61466.2024.10577740","type":"proceedings-article","created":{"date-parts":[[2024,7,5]],"date-time":"2024-07-05T17:15:32Z","timestamp":1720199732000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Provably Correct SGD-Based Exploration for Generalized Stochastic Bandit Problem"],"prefix":"10.1109","author":[{"given":"Jialin","family":"Dong","sequence":"first","affiliation":[{"name":"University of California,Los Angeles,CA,US,90095"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Utah,Salt Lake City,UT,US,84112"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin F.","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California,Los Angeles,CA,US,90095"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3008091"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2014.2365803"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900280"},{"key":"ref5","first-page":"2312","article-title":"Improved al-gorithms for linear stochastic bandits","author":"Abbasi-Yadkori","year":"2011","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Eluder dimension and the sample complexity of optimistic exploration","volume":"26","author":"Russo","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref8","first-page":"41","article-title":"Towards minimax policies for online linear optimization with bandit feedback","volume-title":"Conference on Learning Theory","author":"Bubeck","year":"2012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9619"},{"key":"ref10","first-page":"1585","article-title":"An efficient algorithm for generalized linear bandit: Online stochastic gradient descent and thompson sampling","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ding","year":"2021"},{"key":"ref11","article-title":"Generalized linear bandits with local differential privacy","volume":"34","author":"Han","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","first-page":"2229","article-title":"An optimal algorithm for bandit convex optimization with strongly-convex and smooth loss","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Ito","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.4171\/msl\/17"},{"key":"ref14","first-page":"4008","article-title":"Efficient bandit convex optimization: Beyond linear losses","volume-title":"Conference on Learning Theory","author":"Suggala","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref17","volume-title":"Introduction to reinforcement learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref18","first-page":"99","article-title":"Scalable generalized linear bandits: Online computation and hashing","author":"Jun","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","first-page":"2071","article-title":"Provably optimal algorithms for generalized linear contextual bandits","volume-title":"Proceedings of the 34th International Conference on Machine Learning- Volume 70","author":"Li","year":"2017"}],"event":{"name":"2024 International Conference on Smart Applications, Communications and Networking (SmartNets)","start":{"date-parts":[[2024,5,28]]},"location":"Harrisonburg, VA, USA","end":{"date-parts":[[2024,5,30]]}},"container-title":["2024 International Conference on Smart Applications, Communications and Networking (SmartNets)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10577635\/10577636\/10577740.pdf?arnumber=10577740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T04:11:02Z","timestamp":1720411862000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10577740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,28]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/smartnets61466.2024.10577740","relation":{},"subject":[],"published":{"date-parts":[[2024,5,28]]}}}