{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T19:26:44Z","timestamp":1745695604987,"version":"3.37.3"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tsp.2023.3316887","type":"journal-article","created":{"date-parts":[[2023,9,20]],"date-time":"2023-09-20T18:04:10Z","timestamp":1695233050000},"page":"3695-3709","source":"Crossref","is-referenced-by-count":2,"title":["Lazy Queries Can Reduce Variance in Zeroth-Order Optimization"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8492-0037","authenticated-orcid":false,"given":"Quan","family":"Xiao","sequence":"first","affiliation":[{"name":"Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4222-5964","authenticated-orcid":false,"given":"Qing","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangdong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3477-1439","authenticated-orcid":false,"given":"Tianyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical, Computer, and Systems Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA"}]}],"member":"263","reference":[{"key":"ref13","first-page":"385","article-title":"Online convex optimization in the bandit setting: Gradient descent without a gradient","author":"flaxman","year":"0","journal-title":"Proc SIAM Symp Discrete Algorithms"},{"key":"ref57","first-page":"4","article-title":"Understanding gradient clipping in private SGD: A geometric perspective","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1561\/9781680831719"},{"key":"ref56","first-page":"3100","article-title":"Improved zeroth-order variance reduced algorithms and analysis for nonconvex optimization","author":"ji","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2409256"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2023.3316887"},{"key":"ref14","first-page":"28","article-title":"Optimal algorithms for online convex optimization with multi-point bandit feedback","author":"agarwal","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref58","first-page":"4","article-title":"SignSGD with majority vote is communication efficient and fault tolerant","author":"bernstein","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref53","first-page":"1356","article-title":"Stochastic zeroth-order optimization in high dimensions","author":"wang","year":"0","journal-title":"Proc Int Conf Artif Intell Statist Lanzarote Canary Islands"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3048237"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5016-8"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1137\/21M1392966"},{"key":"ref10","first-page":"928","article-title":"Online convex programming and generalized infinitesimal gradient ascent","author":"zinkevich","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","first-page":"4","article-title":"Gradientless descent: High-dimensional zeroth-order optimization","author":"golovin","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref17","first-page":"1703","article-title":"An optimal algorithm for bandit and zero-order convex optimization with two-point feedback","volume":"18","author":"shamir","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2020.3029304"},{"key":"ref18","first-page":"3727","article-title":"Zeroth-order stochastic variance reduction for nonconvex optimization","author":"liu","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2997394"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2896025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3162958"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2839563"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3214122"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301742"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/110831659"},{"key":"ref41","first-page":"3","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","author":"sun","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"3","article-title":"SIGNSGD via zeroth-order oracle","author":"liu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/120880811"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.3029983"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2896243"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096612"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003837"},{"key":"ref4","first-page":"2","article-title":"Learning to learn by zeroth-order oracle","author":"ruan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01360"},{"key":"ref6","first-page":"4","article-title":"On the convergence theory for Hessian-free bilevel algorithms","author":"sow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"4","article-title":"ES-MAML: Simple Hessian-free meta learning","author":"song","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref40","first-page":"3","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","first-page":"9712","article-title":"Linear bandits with stochastic delayed feedback","author":"vernade","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"3285","article-title":"An optimal algorithm for adversarial bandits with arbitrary delays","author":"zimmert","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref37","first-page":"2","article-title":"On the convergence of prior-guided zeroth-order optimization algorithms","volume":"34","author":"cheng","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","first-page":"2","article-title":"Stochastic bandits with arm-dependent delays","author":"manegueu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"1453","article-title":"Online learning under delayed feedback","author":"joulani","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","first-page":"2938","article-title":"Improved regret for zeroth-order stochastic convex bandits","author":"lattimore","year":"0","journal-title":"Proc Conf Learn Theory"},{"key":"ref33","first-page":"993","article-title":"Bandit online learning with unknown delays","author":"li","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref32","first-page":"1270","article-title":"Online learning with adversarial delays","author":"quanrud","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"article-title":"Evolution strategies as a scalable alternative to reinforcement learning","year":"2017","author":"salimans","key":"ref1"},{"key":"ref39","first-page":"3","article-title":"Improve single-point zeroth-order optimization using high-pass and low-pass filters","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"article-title":"Boosting one-point derivative-free online optimization via residual feedback","year":"0","author":"zhang","key":"ref38"},{"key":"ref24","first-page":"1","article-title":"Stochastic zeroth-order optimization under nonstationarity and nonconvexity","volume":"23","author":"roy","year":"2022","journal-title":"J Mach Learn Res"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096148"},{"key":"ref26","first-page":"697","article-title":"Nearly tight bounds for the continuum-armed bandit problem","author":"kleinberg","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(96)00149-5"},{"key":"ref20","first-page":"4","article-title":"Reserve price optimization for first price auctions in display advertising","author":"feng","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"4","article-title":"Learning supervised pagerank with gradient-based and gradient-free optimization methods","author":"bogolubsky","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","first-page":"397","article-title":"Online boosting with bandit feedback","author":"brukhim","year":"2021","journal-title":"Proc Algorithmic Learning Theory"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1561\/2200000068"},{"key":"ref27","first-page":"4172","article-title":"Gradient-free online learning in continuous games with delayed rewards","author":"h\u00e9liou","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3055399.3055403"},{"key":"ref60","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","author":"fazel","year":"0","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/10040758\/10256140.pdf?arnumber=10256140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,8]],"date-time":"2023-11-08T19:15:49Z","timestamp":1699470949000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10256140\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tsp.2023.3316887","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2023]]}}}