Asynchronous Broadcast-Based Convex Optimization Over a Network
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
We consider a distributed multi-agent network system where each agent has its own convex objective function, which can be evaluated with stochastic errors. The problem consists of minimizing the sum of the agent functions over a commonly known constraint set, but without a central coordinator and without agents sharing the explicit form of their objectives. We propose an asynchronous broadcast-based algorithm where the communications over the network are subject to random link failures. We investigate the convergence properties of the algorithm for a diminishing (random) stepsize and a constant stepsize, where each agent chooses its own stepsize independently of the other agents. Under some standard conditions on the gradient errors, we establish almost sure convergence of the method to an optimal point for diminishing stepsize. For constant stepsize, we establish some error bounds on the expected distance from the optimal point and the expected function value. We also provide numerical results.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Consensus Problems in Networks of Agents With Switching Topology and Time-Delays
Olfati-Saber, R., & Murray, R. M. (2004) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2004.834113 · Cited by 12,788 · cited 1×
“Since we are dealing with a random broadcast scheme for consensus, on a broader scale our work in this paper is related to the literature on distributed consensus and averaging [30], [31], [3], [12], [22], [32], [15], [18], [21].”
BackgroundCoordination of groups of mobile autonomous agents using nearest neighbor rules
Jadbabaie, A., Lin, J., & Morse, A. S. (2003) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2003.812781 · Cited by 8,339
PE, & Billingsley, P. (1996) · Journal of the American Statistical Association · doi:10.2307/2291440 · Cited by 6,481
Parallel and Distributed Computation: Numerical Methods
Bertsekas, D. P., & Tsitsiklis, J. N. (1989) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 5,293
Distributed Subgradient Methods for Multi-Agent Optimization
Nedic, A., & Ozdaglar, A. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2009515 · Cited by 3,719 · cited 1×
“The agent (that has just updated the iterate) passes the iterate to a randomly selected neighbor to perform the next update.”
BackgroundBoyd, S., Ghosh, A., Prabhakar, B., & Shah, D. (2006) · IEEE Transactions on Information Theory · doi:10.1109/tit.2006.874516 · Cited by 2,439 · cited 1×
“As in [6], [7], [27], we find it easier to study the algorithm in terms of a single virtual clock that ticks whenever any of the local Poisson clock ticks.”
BackgroundConvex Analysis and Optimization
Bertsekas, D. P., Nedić, A., & Ozdaglar, A. (2003) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2,148
Constrained Consensus and Optimization in Multi-Agent Networks
Nedic, A., Ozdaglar, A., & Parrilo, P. A. (2010) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2010.2041686 · Cited by 2,086 · cited 1×
“this paper is related to the literature on distributed consensus and averaging [10], [11], [15]–[17], [19]–[22].”
BackgroundDistributed asynchronous deterministic and stochastic gradient optimization algorithms
Tsitsiklis, J., Bertsekas, D., & Athans, M. (1986) · IEEE Transactions on Automatic Control · doi:10.1109/tac.1986.1104412 · Cited by 1,967
(1989) · Choice Reviews Online · doi:10.5860/choice.26-5109 · Cited by 1,755
Research works printed but not linked: 2
- lobel, 2008, Distributed subgradient methods over random networks
- ram, 2010, Sensor Networks When Theory Meets Practice
Cited by
Items 101–200 of 326
Asynchronous Optimization Over Graphs: Linear Convergence Under Error Bound Conditions
Cannelli, L., Facchinei, F., Scutari, G., & Kungurtsev, V. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3033490 · Cited by 27
“(a) Random activation and no delays [20]–[27], [40]: While substantially different in the form of the updates performed by the agents, these schemes are all asynchronous in the sense of feature (i) only.”
BackgroundStochastic sub-gradient algorithm for distributed optimization with random sleep scheme
Yi, P., & Hong, Y. (2015) · Control Theory and Technology · doi:10.1007/s11768-015-5100-8 · Cited by 26
“We first characterize the stepsize in the following lemma, which can be proved with the law of the iterated logarithm ([29]), and whose proof details can also be found in [9] and are omitted here.”
BackgroundMethodInfluentialAn asynchronous distributed gradient algorithm for economic dispatch over stochastic networks
Zhang, H., Liang, S., Ou, M., & Wei, M. (2020) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2020.106240 · Cited by 26
The Smallest Possible Interaction Radius for Synchronization of Self-Propelled Particles
Chen, G., Liu, Z., & Guo, L. (2014) · SIAM Review · doi:10.1137/140961249 · Cited by 27
Approximate Projection Methods for Decentralized Optimization With Functional Constraints
Lee, S., & Zavlanos, M. M. (2017) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2017.2778696 · Cited by 25
A Sharp Convergence Rate Analysis for Distributed Accelerated Gradient MethodsPreprint
Li, H., Fang, C., Yin, W., & Lin, Z. (2018) · arXiv (Cornell University) · Cited by 25
Riemannian Optimization for Active Mapping With Robot Teams
Asgharivaskasi, A., Girke, F., & Atanasov, N. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3526295 · Cited by 25
A Gradient Tracking Protocol for Optimization Over Nabla Fractional Multi-Agent Systems
Zhou, S., Wei, Y., Liang, S., & Cao, J. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3402354 · Cited by 24
“For example, many algorithms require all agents to use the same step-size, which can be challenging in some situations like random networks [29].”
BackgroundManzoor, H. U., Habib, U., Hussain, S., Flynn, D., & Zoha, A. (2024) · Energy and Buildings · doi:10.1016/j.enbuild.2024.114871 · Cited by 25
Williams, R. K., Gasparri, A., Priolo, A., & Sukhatme, G. S. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2014.2315713 · Cited by 24
D-DistADMM: A O(1/k) Distributed ADMM for Distributed Optimization in Directed Graph Topologies
Khatana, V., & Salapaka, M. V. (2020) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9304086 · Cited by 24
“edu} are with Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, USA, (sub)-gradient based methods and a number of existing schemes to minimize finite sum of convex function lie in this category with beginnings in the Distributed Gradient Descent (DGD) [7], the stochastic and asyn…”
MethodFlexPD: A Flexible Framework of First-Order Primal-Dual Algorithms for Distributed Optimization
Mansoori, F., & Wei, E. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3083981 · Cited by 23
“Stochastic and asynchronous versions of DGD are presented in [34, 26].”
BackgroundResilient Control of Transportation Networks by Using Variable Speed Limits
Yazıcıoğlu, Y., Roozbehani, M., & Dahleh, M. A. (2017) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2782364 · Cited by 24
“, see [36], [37], and the references therein).”
BackgroundAsynchronous broadcast-based decentralized learning in sensor networks
Zhao, L., Song, W., Ye, X., & Gu, Y. (2017) · International Journal of Parallel Emergent and Distributed Systems · doi:10.1080/17445760.2017.1294690 · Cited by 23
“Assuming nodes i ∈ J k receive the estimate x i k k − 1 ( i k is the index of the node selected at iteration k ), Nedic’s update rule can be expressed as follows.”
BackgroundMethodInfluentialDistributed consensus-based multi-agent convex optimization via gradient tracking technique
Li, H., Zhang, H., Wang, Z., Zhu, Y., & Han, Q. (2019) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2019.01.050 · Cited by 23
Primal–Dual Fixed Point Algorithms Based on Adapted Metric for Distributed Optimization
Li, H., Zheng, Z., Lü, Q., Wang, Z., Gao, L., Wu, G., Ji, L., & Wang, H. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3110295 · Cited by 23
“In addition, Algorithm 2 can activate multiple agents per iteration, which is more practical than the asynchronous algorithms [32], [58] with a single agent activation.”
BackgroundA Distributed Algorithm for Solving Linear Algebraic Equations Over Random Networks
Alaviani, S. S., & Elia, N. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8618709 · Cited by 25
Asynchronous Algorithms for Decentralized Resource Allocation Over Directed Networks
Lü, Q., Liao, X., Deng, S., & Li, H. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3212424 · Cited by 22
“[30] Let the scalar " satisfy 0 " 1 = 2 .”
MethodLin, P., & Ren, W. (2012) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2012.6425866 · Cited by 22
Li, H., Fang, C., & Lin, Z. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.10802 · Cited by 21
“Existing decentralized algorithms include the distributed subgradient (gradient) method [11, 12, 13, 14, 15, 16, 17], the fast gradient method [18], the dual averaging method [19], the dual decomposition [20], ADMM [21, 22, 23] and EXTRA [10, 24].”
MethodYan, J., Shi, X., Guo, L., Wan, Y., & Wen, G. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3407660 · Cited by 21
“In such a situation, the distributed subgradient algorithm [15] and its variants [16], [17] can be employed to tackle the composite optimization problem.”
MethodPrivate Learning on NetworksPreprint
Gade, S., & Vaidya, N. H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.05236 · Cited by 21
“Keywords – Distributed optimization, privacy preservation, distributed learning, networks.”
BackgroundDistributed Subgradient Algorithm for Multi-Agent Optimization With Dynamic Stepsize
Ren, X., Li, D., Xi, Y., & Shao, H. (2021) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2021.1003904 · Cited by 20
“The recent developed distributed algorithms with fixed stepsizes [14]–[18] achieve linear convergence to the optimal solution.”
BackgroundA stochastic coordinate descent primal-dual algorithm and applications
Bianchi, P., Hachem, W., & Iutzeler, F. (2014) · Machine learning for signal processing ... · doi:10.1109/mlsp.2014.6958866 · Cited by 20
“- ABG: the asynchronous broadcast gradient [42].”
Decentralized Consensus Optimization and Resource Allocation
Nedić, A., Olshevsky, A., & Shi, W. (2018) · Lecture notes in mathematics · doi:10.1007/978-3-319-97478-1_10 · Cited by 18
Morral, G., Bianchi, P., & Fort, G. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2666771 · Cited by 19
“A couple of works (see e.g. [14], [24]) get rid of the column-stochasticity condition, but at the price of assumptions that may not always be satisfied in practice.”
BackgroundConvergence of Distributed Accelerated Algorithm Over Unbalanced Directed Networks
Li, H., Lü, Q., Chen, G., Huang, T., & Dong, Z. Y. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2946287 · Cited by 19
“In addition, extensions to various realistic factors and technologies containing stochastic (sub)gradient errors [22], [23], switching topologies [24], uncoordinated local constraints [25], [26], random link failures [27], and distributed charging control [28] have been studied extensively.”
BackgroundAsynchronous Decentralized Accelerated Stochastic Gradient Descent
Lan, G., & Zhou, Y. (2021) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2021.3080256 · Cited by 19
“While asynchronous decentralized stochastic firstorder methods [33], [34] established error bounds when fi is (strongly) convex, [35] achieved O(1/ 2) rate of convergence for smooth and convex problems.”
BackgroundHuang, C., Li, H., Xia, D., & Xiao, L. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.12.043 · Cited by 18
Fast and Differentially Private Algorithms for Decentralized Collaborative Machine LearningPreprint
Bellet, A., Guerraoui, R., Taziki, M., & Tommasi, M. (2017) · arXiv (Cornell University) · Cited by 18
Asynchronous Subgradient-Push.Preprint
Assran, M., & Rabbat, M. (2018) · arXiv (Cornell University) · Cited by 19
Optimized Gradient Tracking for Decentralized Online Learning
Sharma, S. D., & Rajawat, K. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3366437 · Cited by 17
“In this context, decentralized online learning algorithms have been well-studied in the last decade [1], [2], [3], [4], [5], [6], [7], [8], [9].”
BackgroundAn asynchronous, forward-backward, distributed generalized Nash equilibrium seeking algorithm
Cenedese, C., Belgioioso, G., Grammatico, S., & Cao, M. (2019) · European Control Conference (ECC) · doi:10.23919/ecc.2019.8795952 · Cited by 17
“During the past years, several asynchronous algorithms for distributed convex optimization were proposed [8], [9], converging under different assumptions.”
BackgroundRandom Sleep Scheme-Based Distributed Optimization Algorithm Over Unbalanced Time-Varying Networks
Li, H., Wang, Z., Xia, D., & Han, Q. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2945864 · Cited by 17
“Assumption 3 [7]: For all i ∈ V and k ≥ 0, let the step-size α i ( k ) = 1 /(cid:9) i ( k ) , where (cid:9) i ( k ) denotes the number of times that agent i has been placed in activated mode until time k .”
BackgroundMethodInfluentialA decentralized framework of unit commitment for future power markets
Li, M., & Luh, P. B. (2013) · IEEE Power Engineering Society General Meeting · doi:10.1109/pesmg.2013.6672790 · Cited by 17
Privacy-Preserving Distributed Analytics in Fog-Enabled IoT Systems
Zhao, L. (2020) · Sensors · doi:10.3390/s20216153 · Cited by 17
“A random broadcast based asynchronous algorithm is designed in [33], which adopts a gradient-based computation scheme for local nodes.”
MethodAsynchronous Stochastic Gradient Descent Over Decentralized Datasets
Du, Y., & You, K. (2021) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2021.3059848 · Cited by 18
Asynchronous Decentralized Optimization in Directed NetworksPreprint
Zhang, J., & You, K. (2019) · arXiv (Cornell University) · Cited by 17
Asynchronous decentralized optimization in heterogeneous systems
Rabbat, M., & Tsianos, K. I. (2014) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2014.7039532 · Cited by 15
“An asynchronous distributed subgradient method using broadcast communications is studied in [18], where it is assumed that all nodes perform local gradient 53rd IEEE Conference on Decision and Control December 15-17, 2014.”
MethodDistributed algorithms for optimization problems with equality constraints
Matei, I., & Baras, J. S. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760232 · Cited by 16
“Analyses of asynchronous versions of the algorithm can be found in [13], [19].”
BackgroundWang, J., & Pham, K. D. (2018) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2018.2867154 · Cited by 16
“Further extensions have been made for constrained optimization in multiagent networks [27], over random networks [28], and using an asynchronous broadcast-based method [29].”
BackgroundMethodOn Consensus-Based Distributed Blind Calibration of Sensor Networks
Stanković, M. S., Stankovic, S. S., Johansson, K. H., Beko, M., & Camarinha-Matos, L. M. (2018) · Sensors · doi:10.3390/s18114027 · Cited by 16
Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning
Adjodah, D., Calacci, D., Dubey, A., Goyal, A., Krafft, P. M., Moro, E., & Pentland, A. (2020) · Adaptive Agents and Multi-Agents Systems · doi:10.65109/lvjf2437 · Cited by 19
“On the other hand, work in the networked optimization literature has demonstrated that the network structure of communication between nodes significantly affects the convergence rate and accuracy of multi-agent learning [20–22].”
BackgroundMethodPrivacy Protection Decentralized Economic Dispatch Over Directed Networks With Accurate Convergence
Lü, Q., Deng, S., Li, H., & Huang, T. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2023.3299294 · Cited by 15
“In Algorithm 1, the local step-size γ ti , i ∈ V , is a diminishing step-size defined by the relative frequency of the generator i ’s updates, i.e. , γ ti = 1 / Γ ti , where Γ ti indicates the number of updates that generator i has conducted until time t [43].”
BackgroundMethodZhou, Y., Li, D., Lu, J., Xi, Y., & Cen, L. (2017) · IET Control Theory and Applications · doi:10.1049/iet-cta.2017.0674 · Cited by 15
Distributed Optimization Over Dependent Random Networks
Aghajan, A., & Touri, B. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3216970 · Cited by 15
“A special case of [18] is the asynchronous gossip algorithm that was introduced in [19].”
BackgroundMethodAlmost sure convergence of a randomized algorithm for relative localization in sensor networks
Ravazzi, C., Frasca, P., Tempo, R., & Ishii, H. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760638 · Cited by 15
“We refer the reader to [12] for randomised asynchronous algorithms for convex optimisation and to [13] for other randomized algorithms in systems and control.”
MethodASY-SONATA: Achieving Geometric Convergence for Distributed Asynchronous Optimization.
Tian, Y., Sun, Y., Du, B., & Scutari, G. (2018) · Cited by 14
Zeroth-order Feedback Optimization for Cooperative Multi-Agent Systems
Tang, Y., Ren, Z., & Li, N. (2020) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9304302 · Cited by 14
“Therefore, our problem can also be viewed from the perspective of distributed optimization with delays [7], [25]–[28].”
BackgroundNaderi, S., & Blondin, M. J. (2023) · IEEE Access · doi:10.1109/access.2023.3341295 · Cited by 14
“Although most of the existing DSG algorithms have been developed for coordinated step-sizes, i.e., when the step-size is the same for all agents in the network, there are some papers investigating uncoordinated step-size [48], [49].”
MethodInexact dual averaging method for distributed multi-agent optimization
Yuan, D., Ho, D. W. C., & Xu, S. (2014) · Systems & Control Letters · doi:10.1016/j.sysconle.2014.06.008 · Cited by 14
Distributed optimization of strongly convex functions on directed time-varying graphs
Nedić, A., & Olshevsky, A. (2013) · IEEE Global Conference on Signal and Information Processing · doi:10.1109/globalsip.2013.6736882 · Cited by 14
“Our work in this paper contributes to the growing literature on distributed methods for optimization over networks [16], [10], [5], [9], [8], [22], [12], [2], [19], [4], [11], and the closely related to [23]–[25].”
MethodDiffusion LMS With Correlated Regressors II: Performance
Piggott, M. J., & Solo, V. (2017) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2017.2703677 · Cited by 14
“In evaluating related work, the reader should not be confused by the large literature on distributed optimization under various - often quite general and stochastic - network conditions: many assume the cost functions are known to each agent [28], [37], others rely on certain uniform boundedness assumptions which do n…”
BackgroundA General Framework of Exact Primal-Dual First-Order Algorithms for Distributed Optimization
Mansoori, F., & Wei, E. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029902 · Cited by 13
“These methods include different variations of distributed (sub)gradient descent (DGD) [7], [12], [21], [22], [25], [27], [28].”
MethodDistributed Optimization of Convex Sum of Non-Convex FunctionsPreprint
Gade, S., & Vaidya, N. H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.05401 · Cited by 14
“Recently, a few papers [18–20] have dealt with distributed non-convex optimization 1 .”
BackgroundHerrera, D. P., Chen, Z., & Larsson, E. G. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3540133 · Cited by 13
“Although multi-agent optimization with broadcast-based communication has been considered in [31], [32], these works focus on convergence analysis and do not optimize communication dynamics.”
Distributed Stochastic Optimization with Gradient Tracking over Time- Varying Directed Networks
Nguyen, D. T. A., Nguyen, D. T., & Nedić, A. (2023) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf59524.2023.10477004 · Cited by 13
Communication-efficient Distributed Multi-resource Allocation
Alam, S. E., Shorten, R. N., Wirth, F. R., & Yu, J. Y. (2018) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc2.2018.8656964 · Cited by 13
“While this body of work is too numerous to enumerate, we point the interested readers to the works of Nedic [5],[6]; Cortes [7]; Jadbabaie and Morse[8]; Bullo [9]; Pappas [10], Bersetkas [11]; Tsitsiklis [12] for recent contributions.”
BackgroundDistributed Optimization Over Networks
Nedić, A. (2018) · Lecture notes in mathematics · doi:10.1007/978-3-319-97142-1_1 · Cited by 13
Success and failure of adaptation-diffusion algorithms for consensus in multi-agent networks
Morral, G., Bianchi, P., & Fort, G. (2014) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2014.7039609 · Cited by 13
“In this section, we consider the general setting described by Algorithm (1)-(2) with weaker conditions on the distribution of the observations Yn.”
BackgroundPrivate Learning on Networks: Part IIPreprint
Gade, S., & Vaidya, N. H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.09185 · Cited by 13
Su, L., Hua, Y., Dong, X., Lü, J., & Ren, Z. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3440349 · Cited by 12
“From[49], it can be obtained that”
BackgroundRigidity-Preserving Team Partitions in Multiagent Networks
Carboni, D., Williams, R. K., Gasparri, A., Ulivi, G., & Sukhatme, G. S. (2014) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2014.2378552 · Cited by 12
“Assumption 1 (Asynchronicity): We assume an asynchronous model of time, where each agent i ∈ I has a clock which ticks according to some distribution with bounded support (allowing for finite termination), independently of the clocks of the other agents [52] (allowing also for the possibility of delayed communication…”
BackgroundYi, P., & Li, L. (2021) · Journal of Systems Science and Complexity · doi:10.1007/s11424-020-0071-3 · Cited by 12
Provably Accelerated Decentralized Gradient Methods Over Unbalanced Directed Graphs
Song, Z., Shi, L., Pu, S., & Yan, M. (2024) · SIAM Journal on Optimization · doi:10.1137/22m148570x · Cited by 11
Robustness Against Data Integrity Attacks in Decentralized Federated Load Forecasting
Shabbir, A., Manzoor, H. U., Manzoor, M. Z., Hussain, S., & Zoha, A. (2024) · Electronics · doi:10.3390/electronics13234803 · Cited by 11
A non-heuristic distributed algorithm for non-convex constrained optimization
Matei, I., & Baras, J. S. (2013) · University Libraries (University of Maryland) · Cited by 11
Nash Equilibrium Seeking with Non-doubly Stochastic Communication Weight Matrix
Salehisadaghiani, F., & Pavel, L. (2017) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-319-67540-4_1 · Cited by 11
Wang, J., Li, H., & Wang, Z. (2019) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2019.0144 · Cited by 11
“In order to get a better convergence rate, constant step-size is considered in [17, 19], but they have the disadvantage of inaccurate convergence to the optimal solution.”
BackgroundGraph Simplification-Aided ADMM for Decentralized Composite Optimization
Wang, B., Fang, J., Duan, H., & Li, H. (2019) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2953538 · Cited by 11
“To accommodate general networks, a distributed subgradient descent (DGD) method [17] and its variants [18], [19] were proposed.”
MethodDistributed stochastic approximation: The price of non-double stochasticity
Morral, G., Bianchi, P., Fort, G., & Jakubowicz, J. (2012) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2012.6489272 · Cited by 11
“Very recently, [12], [16], [17] get rid the column stochasticity condition and prove that convergence to the sought consensus can indeed be achieved using rather simple communication protocols of broadcast nature.”
BackgroundMulti-cluster distributed optimization via random sleep strategy
Shi, C., & Yang, G. (2019) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2019.03.021 · Cited by 11
Nash Equilibrium Seeking with Non-doubly Stochastic Communication Weight Matrix
Salehisadaghiani, F., & Pavel, L. (2019) · EAI Endorsed Transactions on Collaborative Computing · doi:10.4108/eai.13-7-2018.158526 · Cited by 11
“Our techniques are also similar to those used in the literature on distributed optimization [17], [20].”
BackgroundMethodInfluentialHybrid Decentralized Data Analytics in Edge-Computing-Empowered IoT Networks
Zhao, L., Li, F., & Valero, M. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3040657 · Cited by 11
“Notice that the scheme proposed in [15] , it is approximately equivalent to run gradient descent using multiple nodes’ data (multiple F i s ).”
BackgroundMethodInfluentialDistributed optimization with applications to sensor networks and machine learning
Srivastava, K. (2011) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · Cited by 11
Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed NetworksPreprint
Nguyen, D. T. A., Wang, S., Nguyen, D. T., Nedić, A., & Poor, H. V. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.17189 · Cited by 11
“Existing literature on decentralized learning and optimization focuses on consensus-based protocols and gradient descent methods for addressing both deterministic problems [21], [22] and stochastic problems [23], [24].”
BackgroundCollaborative Multi-Agent Video Fast-Forwarding
Lan, S., Wang, Z., Wei, E., Roy–Chowdhury, A. K., & Zhu, Q. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3275853 · Cited by 10
“Follow-up works [53], [54], [55] extend this method to other settings, including stochastic networks, constrained problems, and noisy environments.”
BackgroundDecentralized and Parallel Constructionsfor Optimally Rigid Graphs in
Gasparri, A., Williams, R. K., Priolo, A., & Sukhatme, G. S. (2015) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2015.2393856 · Cited by 10
ET-DASG: An Efficient Decentralized Algorithm for Convex Optimization Over Networks
Lü, Q., Liao, X., Deng, S., & Li, H. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3153386 · Cited by 10
Distributed shortest distance consensus problem in multi-agent systems
Lin, P., & Ren, W. (2012) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2012.6425861 · Cited by 10
Distributed Maximum Likelihood Using Dynamic Average Consensus
George, J. (2018) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2018.8461529 · Cited by 10
“While DSMs have the advantage of being easily distributed, have limited computational requirements, and are inherently asynchronous [12]–[14], they suffer from a low convergence rate since they require the update step size to decrease to zero as k → ∞ (k being the iteration step).”
BackgroundDistributed primal-dual optimisation method with uncoordinated time-varying step-sizes
liu, P. L., Li, H., Dai, X., & Han, Q. (2018) · International Journal of Systems Science · doi:10.1080/00207721.2018.1442886 · Cited by 10
“Afterwards, to tackle with the more general networks, a new sub-gradient algo-rithm is presented in Nedic and Ozdaglar (2009), followed by its stochastic and asynchronous variant in Nedic (2011) and Sundhar Ram, Nedi´c, and Veeravalli (2010).”
BackgroundDistributed Optimization over General Directed Networks with Random Sleep Scheme
Wang, Z., Zheng, L., & Li, H. (2020) · International Journal of Control Automation and Systems · doi:10.1007/s12555-018-9543-9 · Cited by 10
Asynchronous Decentralized Successive Convex ApproximationPreprint
Tian, Y., Sun, Y., & Scutari, G. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.10144 · Cited by 10
“Specifically, [3,15,22,46] can only tolerate packet losses (either the information gets lost or is received with no delay); [1] handles only communication delays (eventually all the transmitted information is received by the intended agent); and [28,41] assume that the agents’ activation and delay as independent rando…”
BackgroundNedić, A. (2015) · Springer eBooks · doi:10.1007/978-1-4471-5058-9_219 · Cited by 10
Distributed multi-agent convex optimization over random digraphs
Alaviani, S. S., & Elia, N. (2017) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2017.7963776 · Cited by 9
“In [25], the author considers a constrained distributed convex optimization over random undirected graphs.”
BackgroundInfluentialCommunication-Efficient Semihierarchical Federated Analytics in IoT Networks
Zhao, L., Valero, M., Pouriyeh, S., Li, L., & Sheng, Q. Z. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3137757 · Cited by 9
“In addition, η ik is upper bounded by ( 2 n / kp min ) [50, Lemma 3] where p min is the minimum among all the probabilities p ij for edge server j to receive i ’s broadcast.”
BackgroundOn the Linear Convergence of Two Decentralized Algorithms
Li, Y., & Yan, M. (2021) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-021-01833-y · Cited by 9
Asynchronous Gossip-Based Random Projection Algorithms Over NetworksPreprint
Lee, S., & Nedić, A. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1304.1757 · Cited by 10
MUSIC: Accelerated Convergence for Distributed Optimization With Inexact and Exact Methods
Wu, M., Liao, H., Ding, Z., & Xiao, Y. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3376421 · Cited by 8
“The corresponding asynchronous and stochastic versions with convergence rate analysis are proposed in [21] and [22], respectively.”
Gossip-based distributed stochastic mirror descent for constrained optimization
Fang, X., Zhang, B., & Yuan, D. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106291 · Cited by 8
Liu, W., & Hua, Z. (2013) · IET Control Theory and Applications · doi:10.1049/iet-cta.2013.0363 · Cited by 8
An extension of the method of multipliers for distributed nonlinear programming
Matei, I., Baras, J. S., Nabi, M., & Kurtoglu, T. (2014) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2014.7040481 · Cited by 8
“Consensusbased distributed optimization algorithms were further used to solve constrained convex optimization problems where all agents have the same constraint set [9], [14], [17] or where each agent has its own set of constraints [15], [19].”
BackgroundMethodDistributed Multi-Objective Optimization over Randomly Varying Unbalanced Networks
Wada, T., Masubuchi, I., Hanada, K., Asai, T., & Fujisaki, Y. (2017) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2017.08.434 · Cited by 8
Distributed Multi-agent Video Fast-forwarding
Lan, S., Wang, Z., Roy–Chowdhury, A. K., Wei, E., & Zhu, Q. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413767 · Cited by 7
“Follow-up works [16, 19, 26, 29, 30, 32] extend this method to other settings, include stochastic network, constrained problems, and noisy environment.”
MethodDistributed Constrained Optimization With Asynchrony and Delays
Su, E., Li, H., Zheng, Z., Lü, Q., & Wang, Z. (2021) · IEEE Transactions on Circuits & Systems II Express Briefs · doi:10.1109/tcsii.2021.3132392 · Cited by 7
“Nedic [14] designed an asynchronous algorithm based on random (one-way) broadcasts that allows random link failures in agents’ communications.”
BackgroundAlaviani, S. S. (2019) · Iowa State University Digital Repository (Iowa State University) · Cited by 7
Nonlinear Programming Methods for Distributed OptimizationPreprint
Matei, I., & Baras, J. S. (2015) · arXiv (Cornell University) · doi:10.13016/m2ng71 · Cited by 7
“…) and John S. Baras is with the Institute for Systems Research at University of Maryland, College Park, MD 20742 ( baras@umd.edu ). graph, [17], [24] study asynchronous versions of the algorithm, [13] considers state-dependent communication topologies, while [5] assumes directed…”
BackgroundMethodInfluentialGradient-Consensus: Linearly Convergent Distributed Optimization Algorithm over Directed GraphsPreprint
Khatana, V., Saraswat, G., Patel, S., & Salapaka, M. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.10070 · Cited by 7
Shi, X., Wan, Y., Wen, G., & Yu, X. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3559905 · Cited by 6
“With a fixed step size, convergence to a neighborhood of the optimal solution is demonstrated in [7], [8].”
Metadata
- Authors
- Nedic, A.
- Venue
- IEEE Transactions on Automatic Control
- Published
- 2011-06
- Volume
- 56
- Issue
- 6
- Pages
- 1337-1351
- ISSN
- 0018-9286 (ISSN-L)
- 1558-2523
- OpenAlex
- W2130263842
- Cited by
- 310
- References
- 36
- Citations by year
- 2026: 2 · 2025: 14 · 2024: 17 · 2023: 12 · 2022: 10 · 2021: 20 · 2020: 38 · 2019: 36 · 2018: 33 · 2017: 30 · 2016: 21 · 2015: 21 · 2014: 21 · 2013: 15 · 2012: 14
- FWCI
- 15.51
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Automatic Control (publishedVersion)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Keywords
- distributed convex optimization, multi-agent systems, random link failures, constant step size, almost sure convergence, error bounds, distributed optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.