{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:33:30Z","timestamp":1763811210632,"version":"3.37.3"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,5,17]]},"DOI":"10.1109\/infocom53939.2023.10228853","type":"proceedings-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T17:40:43Z","timestamp":1693330843000},"page":"1-10","source":"Crossref","is-referenced-by-count":1,"title":["DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization"],"prefix":"10.1109","author":[{"given":"Peiwen","family":"Qiu","sequence":"first","affiliation":[{"name":"The Ohio State University,Dept. of ECE"}]},{"given":"Yining","family":"Li","sequence":"additional","affiliation":[{"name":"The Ohio State University,Dept. of ECE"}]},{"given":"Zhuqing","family":"Liu","sequence":"additional","affiliation":[{"name":"The Ohio State University,Dept. of ECE"}]},{"given":"Prashant","family":"Khanduri","sequence":"additional","affiliation":[{"name":"Wayne State University,Dept. of CS"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"The Ohio State University,Dept. of ECE"}]},{"given":"Ness B.","family":"Shroff","sequence":"additional","affiliation":[{"name":"The Ohio State University,Dept. of ECE"}]},{"given":"Elizabeth","family":"Serena Bentley","sequence":"additional","affiliation":[{"name":"Information Directorate,Air Force Research Laboratory"}]},{"given":"Kurt","family":"Turck","sequence":"additional","affiliation":[{"name":"Information Directorate,Air Force Research Laboratory"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3492866.3549721"},{"key":"ref35","first-page":"6050","article-title":"Stem: A stochastic two-sided momentum algorithm achieving near-optimal sample and communication complexities for federated learning","volume":"34","author":"khanduri","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488686"},{"key":"ref34","first-page":"11459","article-title":"A hybrid variance-reduced method for decentralized stochastic non-convex optimization","author":"xin","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2010.2041686"},{"key":"ref37","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref36","first-page":"1568","article-title":"Bilevel programming for hyperparameter optimization and meta-learning","author":"franceschi","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref31","first-page":"7184","article-title":"On the linear speedup analysis of communication efficient momentum sgd for distributed non-convex optimization","author":"yu","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737489"},{"key":"ref11","first-page":"30271","article-title":"A near-optimal algorithm for stochastic bilevel optimization via double-momentum","volume":"34","author":"khanduri","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-020-01487-0"},{"article-title":"Randomized stochastic variance-reduced methods for stochastic bilevel optimization","year":"2021","author":"guo","key":"ref10"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/DSW.2019.8755807"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6226"},{"article-title":"A two-timescale framework for bilevel optimization: Complexity analysis and application to actor-critic","year":"2020","author":"hong","key":"ref1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.amc.2003.12.089"},{"article-title":"Hybrid stochastic gradient descent algorithms for stochastic nonconvex optimization","year":"2019","author":"tran-dinh","key":"ref39"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.1.37"},{"key":"ref38","article-title":"Momentum-based variance reduction in non-convex sgd","volume":"32","author":"cutkosky","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0176-2"},{"key":"ref18","first-page":"347","article-title":"Penalty method for inversion-free deep bilevel optimization","author":"mehra","year":"2021","journal-title":"Asian Conference on Machine Learning"},{"key":"ref24","first-page":"737","article-title":"Hyperparameter optimization with approximate gradient","author":"pedregosa","year":"2016","journal-title":"International Conference on Machine Learning"},{"article-title":"On differentiating parameterized argmin and argmax problems with application to bi-level optimization","year":"2016","author":"gould","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8430883"},{"journal-title":"Problems in decentralized decision making and computation","year":"1984","author":"tsitsiklis","key":"ref25"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/10556780802102586"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref22","first-page":"1723","article-title":"Truncated backpropagation for bilevel optimization","author":"shaban","year":"2019","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"article-title":"UCI machine learning repository","year":"2017","author":"dheeru","key":"ref44"},{"article-title":"Lower bounds and accelerated algorithms for bilevel optimization","year":"2021","author":"ji","key":"ref21"},{"key":"ref43","first-page":"3748","article-title":"On the iteration complexity of hypergradient computation","author":"grazzi","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1109\/JPROC.2010.2081652","article-title":"Achieving controllability of electric loads","volume":"99","author":"callaway","year":"2010","journal-title":"Proceedings of the IEEE"},{"key":"ref29","article-title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent","volume":"30","author":"lian","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","first-page":"13670","article-title":"Provably faster algorithms for bilevel optimization","volume":"34","author":"yang","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"4882","article-title":"Bilevel optimization: Convergence analysis and enhanced design","author":"ji","year":"2021","journal-title":"International Conference on Machine Learning"},{"article-title":"A single-timescale stochastic bilevel optimization method","year":"2021","author":"chen","key":"ref9"},{"key":"ref4","article-title":"Meta-learning with implicit gradients","volume":"32","author":"rajeswaran","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW53276.2021.9455948"},{"article-title":"Approximation methods for bilevel programming","year":"2018","author":"ghadimi","key":"ref6"},{"journal-title":"Foundations of Bilevel Programming","year":"2002","author":"dempe","key":"ref5"},{"journal-title":"Exploring Network Structure Dynamics and Function Using NetworkX","year":"2008","author":"hagberg","key":"ref40"}],"event":{"name":"IEEE INFOCOM 2023 - IEEE Conference on Computer Communications","start":{"date-parts":[[2023,5,17]]},"location":"New York City, NY, USA","end":{"date-parts":[[2023,5,20]]}},"container-title":["IEEE INFOCOM 2023 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10228851\/10228852\/10228853.pdf?arnumber=10228853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T17:45:10Z","timestamp":1695059110000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10228853\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,17]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/infocom53939.2023.10228853","relation":{},"subject":[],"published":{"date-parts":[[2023,5,17]]}}}