Distributed Subgradient Methods for Convex Optimization Over Random Networks
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
We consider the problem of cooperatively minimizing the sum of convex functions, where the functions represent local objective functions of the agents. We assume that each agent has information about his local function, and communicate with the other agents over a time-varying network topology. For this problem, we propose a distributed subgradient method that uses averaging algorithms for locally sharing information among the agents. In contrast to previous works on multi-agent optimization that make worst-case assumptions about the connectivity of the agents (such as bounded communication intervals between nodes), we assume that links fail according to a given stochastic process. Under the assumption that the link failures are independent and identically distributed over time (possibly correlated across links), we provide almost sure convergence results for our subgradient algorithm.
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×
“[10], OlfatiSaber and Murray [16], Cao et al.”
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
Novel Type of Phase Transition in a System of Self-Driven Particles
Vicsek, T., Czirók, A., Ben-Jacob, E., Cohen, I., & Shochet, O. (1995) · Physical Review Letters · doi:10.1103/physrevlett.75.1226 · Cited by 7,380
Parallel and Distributed Computation: Numerical Methods
Bertsekas, D. P., & Tsitsiklis, J. N. (1989) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 5,293
Rate control for communication networks: shadow prices, proportional fairness and stability
Kelly, F. P., Maulloo, A. K., & Tan, D. K. H. (1998) · Journal of the Operational Research Society · doi:10.1057/palgrave.jors.2600523 · Cited by 5,021 · cited 1×
“[11], Low and Lapsley [12], Srikant [20], and Chiang et al.”
BackgroundDistributed 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 6×
“[23], Bertsekas and Tsitsiklis [2]), which developed a general framework for parallel and distributed computation among different processors, and on the recent work by Nedić and Ozdaglar [14], which studied a distributed method for cooperative optimization in multi-agent environments.”
BackgroundMethodResultInfluentialSelf-citationRate control for communication networks: shadow prices, proportional fairness and stability
Kelly, F. P., Maulloo, A. K., & Tan, D. K. H. (1998) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600523 · Cited by 2,399
Convex Analysis and Optimization
Bertsekas, D. P., Nedić, A., & Ozdaglar, A. (2003) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 2,148
Self-citationConstrained 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×
“The following lemma on the infinite sum of products of the components of two sequences will also be used in establishing our convergence results (see Lemma 7 in [15] for the proof).”
BackgroundSelf-citationOptimization flow control. I. Basic algorithm and convergence
Low, S. H., & Lapsely, D. E. (1999) · IEEE/ACM Transactions on Networking · doi:10.1109/90.811451 · Cited by 1,972 · cited 1×
“[11], Low and Lapsley [12], Srikant [20], and Chiang et al.”
Background
Research works printed but not linked: 1
- bertsimas, 1985, Linear Optimization
Cited by
Items 101–200 of 342
Wen, X., Luan, L., & Qin, S. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.05.020 · Cited by 47
Distributed learning over unreliable networks
Yu, C., Tang, H., Renggli, C., Kassing, S., Singla, A., Alistarh, D., Zhang, C., & Liu, J. (2018) · arXiv · doi:10.48550/arxiv.1810.07766 · Cited by 45
“However, most of the previous work (Li and Zhang, 2010; Lobel and Ozdaglar, 2011) made the assumption that the randomized network should be doubly-stochastic.”
BackgroundLiu, Y., Guo, L., Lu, C., Chai, Y., Gao, S., & Xu, B. (2019) · IEEE Access · doi:10.1109/access.2019.2912004 · Cited by 47
“Existing algorithms can basically be classified into three categories according to the way of dealing with consistency constraints: the primal domain algorithm [19]–[22], the dual domain algorithm [23], [24], and the primal-dual algorithm [25]–[27].”
BackgroundDistributed resource allocation over random networks based on stochastic approximation
Yi, P., Lei, J., & Hong, Y. (2018) · Systems & Control Letters · doi:10.1016/j.sysconle.2018.02.009 · Cited by 45
“To describe uncertainties of communication topologies, different from the deterministic switching graphs in [7, 12] and [13], we adopt random graph models like [9, 10, 23] and [24] here.”
BackgroundMethodInfluentialMultiagent System-Based Integrated Solution for Topology Identification and State Estimation
Zhang, W., Liu, W., Zang, C., & Liu, L. (2016) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2016.2543200 · Cited by 43
“In addition, according to [15] and [16], the distributed subgradient algorithm only requires decomposed local objective functions to be convex, and does not require each local area to be observable.”
BackgroundInfluentialAccelerated dual descent for network optimization
Zargham, M., Ribeiro, A., Ozdaglar, A., & Jadbabaie, A. (2011) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2011.5991367 · Cited by 40
Self-citationS-DIGing: A Stochastic Gradient Tracking Algorithm for Distributed Optimization
Li, H., Zheng, L., Wang, Z., Yan, Y., Feng, L., & Guo, J. (2020) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2020.3017242 · Cited by 40
“More classical results about (sub)gradient method can be found in [8]–[10].”
MethodStochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphs
Nedic, A., & Olshevsky, A. (2014) · arXiv · doi:10.48550/arxiv.1406.2075 · Cited by 38
“Our work here contributes to the growing literature on distributed methods for optimization over networks [5], [9], [12], [14]–[16], [19]–[23], [28], [32], [34], [40], [43].”
MethodAn, W., Zhao, P., Liu, H., & Hu, J. F. (2022) · International Journal of Systems Science · doi:10.1080/00207721.2022.2063967 · Cited by 38
“Since then, plenty of attempts have been made for the extension of the distributed SgAs, see Lobel and Ozdaglar (2011) and the references therein.”
BackgroundContinuous-time Distributed Convex Optimization with Set Constraints
Liu, S., Qiu, Z., & Xie, L. (2014) · IFAC Proceedings Volumes · doi:10.3182/20140824-6-za-1003.01377 · Cited by 39
“The optimization problem under random communication graph is considered in Lobel and Ozdaglar (2011).”
BackgroundMethodDistributed Multiagent Convex Optimization Over Random Digraphs
Alaviani, S. S., & Elia, N. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2019.2937499 · Cited by 41
“The authors of [4] and [8]–[21] assume that the random interconnection graphs are independent and identically distributed (i.”
BackgroundMulti-agent optimization in the presence of Byzantine adversaries: Fundamental limits
Su, L., & Vaidya, N. H. (2016) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.1109/acc.2016.7526806 · Cited by 40
“The failure-free version of the multi-agent optimization problem has received significant attention in recent years [7], [16], [23], [5], [9], [11].”
BackgroundModelling and Simulation Approaches for Local Energy Community Integrated Distribution Networks
Rana, R., Berg, K., Degefa, M. Z., & Löschenbrand, M. (2022) · IEEE Access · doi:10.1109/access.2022.3140237 · Cited by 35
Distributed Optimization With Projection-Free Dynamics: A Frank-Wolfe Perspective
Chen, G., Yi, P., Hong, Y., & Chen, J. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3284822 · Cited by 37
A Distributed Algorithm for Solving Linear Algebraic Equations Over Random Networks
Alaviani, S. S., & Elia, N. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3010264 · Cited by 38
“Furthermore, theresultsin[24],[25],and[27]assumeweightedmatrixofthegraphto beindependentandidenticallydistributed(i.i.d.),whereas[26]assumes weightedmatrixofthegraphtobeastate-dependentMarkovprocess.”
BackgroundDistributed Time-Varying Convex Optimization With Dynamic Quantization
Chen, Z., Yi, P., Li, L., & Hong, Y. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3099905 · Cited by 34
“Fruitful results via continuous time algorithms [8]–[11] or discrete-time algorithms [4]–[7] have been studied in distributed optimization problems, such as gradient/subgradient methods [5], [12] and their accelerated version; dual averaging methods [10], [13]–[15]; diffusion methods [16]; and alternating direction me…”
Matcha: A Matching-Based Link Scheduling Strategy to Speed up Distributed Optimization
Wang, J., Sahu, A. K., Joshi, G., & Kar, S. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3212536 · Cited by 43
“Other meth-ods include gradient quantization [27], asynchronous model aggregation [28], stochastic gradient push [29] and pairwise gossip [18], [30], [31] (see Section VII for a detailed comparison).”
BackgroundDiffusion Adaptation over Multi-Agent Networks with Wireless Link Impairments
Abdolee, R., Champagne, B., & Sayed, A. H. (2015) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2015.2460251 · Cited by 32
“✦”
Stochastic mirror descent method for distributed multi-agent optimization
Li, J., Li, G., Wu, Z., & Wu, C. (2016) · Optimization Letters · doi:10.1007/s11590-016-1071-z · Cited by 36
Distributed Robust Adaptive Optimization for Nonlinear Multiagent Systems
Liu, Y., & Yang, G. (2019) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2019.2894948 · Cited by 32
“Utilizing the method of consensus-based dynamics, this distributed optimization problem has also been considered in [16]–[21] and [25]–[28].”
MethodSampled-data based distributed convex optimization with event-triggered communication
Liu, J., Chen, W., & Dai, H. (2016) · International Journal of Control Automation and Systems · doi:10.1007/s12555-015-0133-9 · Cited by 32
Decentralized Online Learning Methods Based on Weight-Balancing Over Time-Varying Digraphs
Xu, C., Zhu, J., & Wu, D. O. (2018) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2018.2880771 · Cited by 30
Mencagli, G., Vanneschi, M., & Vespa, E. (2014) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/2567929 · Cited by 30
Gong, C., Cheng, Z., Sou, W.-K., Lam, C., & Chow, M. (2023) · IEEE Transactions on Power Delivery · doi:10.1109/tpwrd.2023.3240462 · Cited by 28
Lü, Q., Li, H., Wang, Z., Han, Q., & Ge, W. C. (2019) · IET Control Theory and Applications · doi:10.1049/iet-cta.2018.6026 · Cited by 28
“This tactic showed advantages over other methods (constructing a series of doubly-stochastic consensus matrices) [7, 13].”
MethodResultGradient-Consensus Method for Distributed Optimization in Directed Multi-Agent Networks
Khatana, V., Saraswat, G., Patel, S., & Salapaka, M. V. (2020) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc45564.2020.9147544 · Cited by 29
“Since then, the problem of optimizing the sum of convex functions in a distributed manner has received significant interest [6], [7], [8], [9], [10].”
BackgroundAn RNN-Based Algorithm for Decentralized-Partial-Consensus Constrained Optimization
Xia, Z., Liu, Y., Qiu, J., Ruan, Q., & Cao, J. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3098668 · Cited by 27
Prescribed-time distributed optimization problem with constraints
Li, H., Zhang, M., Yin, Z., Zhao, Q., Xi, J., & Zheng, Y. (2024) · ISA Transactions · doi:10.1016/j.isatra.2024.03.024 · Cited by 26
“Most of the existing works [10–12] concerning about un-constrained distributed optimization, which is difficult to be extended to some practical applications.”
Distributed Bregman-Distance Algorithms for Min-Max Optimization
Srivastava, K., Nedić, A., & Stipanović, D. M. (2012) · Studies in computational intelligence · doi:10.1007/978-3-642-34097-0_7 · Cited by 33
“Recent work in agreement-based distributed optimization has focused on minimizing the sum of agents’ local cost functions [25, 23, 35, 17, 19, 20, 32], which arises in wide variety of areas ranging from sensor networks [28] to distributed machine learning [1].”
BackgroundMethodStochastic 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
“Noisy subgradients may come from the gradient evaluation process or stochastic optimization problems (see [8–10] and [18]).”
BackgroundDistributed convex optimisation with event-triggered communication in networked systems
Liu, J., & Chen, W. (2016) · International Journal of Systems Science · doi:10.1080/00207721.2015.1135358 · Cited by 26
“…network resource allocation (Duchi, Agarwal, & Wainwright, 2012; Gharesifard & Cortés, 2014; Jakovetic, Xavier, & Moura, 2011; Lee & Nedi´c, 2013; Lobel & Ozdaglar, 2011; Lu & Tang, 2012; Matei & Baras, 2011; Nedi´c & Ozdaglar, 2009; Rabbat & Nowak, 2005; Srivastava & Nedi´c, 2011; Zhu &…”
BackgroundMethodInfluentialCloud-based centralized/decentralized multi-agent optimization with communication delays
Hale, M., Nedić, A., & Egerstedt, M. (2015) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402311 · Cited by 25
“Problems with time-varying communication graphs, non-differentiable objective functions, and noisy communication links are considered in [12].”
BackgroundDistributed Stochastic Approximation: Weak Convergence and Network Design
Stanković, M. S., Ilić, N., & Stankovic, S. S. (2016) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2016.2545098 · Cited by 27
“, [9], [10], [11], [18], [19]), assuming double stochasticity of the random communication”
BackgroundApproximate 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
Lv, Y.-W., Yang, G., & Shi, C. (2020) · Information Sciences · doi:10.1016/j.ins.2020.05.119 · Cited by 27
Recycled ADMM: Improve Privacy and Accuracy with Less Computation in Distributed Algorithms
Zhang, X., Khalili, M. M., & Liu, M. (2018) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2018.8635916 · Cited by 31
Distributed Variable Sample-Size Stochastic Optimization With Fixed Step-Sizes
Lei, J., Yi, P., Chen, J., & Hong, Y. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3179216 · Cited by 28
“undirected graphs [47], random gossip and broadcast communications [28], [34], etc.”
BackgroundBroadcast-based distributed alternating direction method of multipliers
Makhdoumi, A., & Ozdaglar, A. (2014) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton.2014.7028466 · Cited by 29
“I. INTRODUCTION”
Self-citationThe 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
“For example, the essential spectrum radius may be used to further study consensus algorithms [19, 20, 21, 22] and distributed optimization [23, 24, 25].”
BackgroundDistributed Stochastic Approximation Algorithm With Expanding Truncations
Lei, J., & Chen, H.-F. (2019) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2019.2912713 · Cited by 21
“3:The DSA algorithm proposed in [10] is based on the RM algorith m: θ̃i,k+1 = θi,k + γkYi,k+1, θi,k+1 = N”
BackgroundMethodPrivate Federated Learning Without a Trusted Server: Optimal Algorithms for Convex LossesPreprint
Lowy, A. M., & Razaviyayn, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09779 · Cited by 27
“In non-private distributed optimization, [LO10, TG15, NOS17] provide convergence results with random connectivity graphs.”
BackgroundA Flocking-Based Approach for Distributed Stochastic Optimization
Pu, S., & García, A. (2017) · Operations Research · doi:10.1287/opre.2017.1666 · Cited by 20
Wang, D., Wang, D., Wang, W., Liu, Y., & Alsaadi, F. E. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.09.016 · Cited by 21
Distributed Gradient Tracking Methods with Finite Data Rates
Ma, X., Yi, P., & Chen, J. (2021) · Journal of Systems Science and Complexity · doi:10.1007/s11424-021-1231-9 · Cited by 19
Accelerated Distributed Dual Averaging Over Evolving Networks of Growing Connectivity
Liu, S., Chen, P., & Hero, A. O. (2018) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2018.2793878 · Cited by 20
Continuous-time distributed algorithms for solving linear algebraic equation
Cao, K., Zeng, X., & Hong, Y. (2017) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2017.8028633 · Cited by 22
Başaran, K., Siano, P., Messlem, A., Candan, A. K., Kivi, M. M., Sakib, M. N., Arikuşu, Y. S., & Lăzăroiu, G. C. (2026) · Energy · doi:10.1016/j.energy.2026.139983 · Cited by 20
Bolognani, S., Carron, A., Vittorio, A. D., Romeres, D., Schenato, L., & Zampieri, S. (2012) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2012.6426317 · Cited by 18
“g.[19], [20], [21]) cannot be directly applied.”
Distributed Weight Selection in Consensus Protocols by Schatten Norm Minimization
Chamie, M. E., Neglia, G., & Avrachenkov, K. E. (2014) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2352773 · Cited by 20
“A distributed computational model for optimizing a sum of non-smooth convex functions is proposed in [15], [16] and its convergence is proved for bounded (sub)gradients for different network dynamics.”
Su, B., Wang, S., & Li, W. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.117383 · Cited by 19
Local Prediction for Enhanced Convergence of Distributed Optimization Algorithms
Mai, V. S., & Abed, E. H. (2017) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2776084 · Cited by 19
Communication-Efficient Distributed Strongly Convex Stochastic Optimization: Non-Asymptotic RatesPreprint
Sahu, A. K., Jakovetić, D., Bajović, D., & Kar, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.02920 · Cited by 22
A 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
Efficient Distributed Optimization of Wind Farms Using Proximal Primal-Dual Algorithms
Annoni, J. R., Dall’Anese, E., Hong, M., & Bay, C. J. (2019) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2019.8814655 · Cited by 17
“Distributed algorithms for convex optimization problems have been developed extensively in the literature (see representative works in [10], [11] and pertinent references therein).”
BackgroundDistributed Mirror Descent over Directed GraphsPreprint
Xi, C., Wu, Q., & Khan, U. A. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.5526 · Cited by 19
Distributed optimization of multi-agent systems with delayed sampled-data
Yan, J., Yu, H., & Xia, X. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.03.036 · Cited by 16
An asynchronous mini-batch algorithm for regularized stochastic optimization
Feyzmahdavian, H. R., Aytekin, A., & Johansson, M. (2015) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402404 · Cited by 19
A Distributed Algorithm for Achieving the Conservation Principle
Wang, X., & Mou, S. (2018) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2018.8431597 · Cited by 18
Swarming for Faster Convergence in Stochastic Optimization
Pu, S., & García, A. (2018) · SIAM Journal on Control and Optimization · doi:10.1137/17m1111085 · Cited by 16
Mencagli, G. (2015) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.3495 · Cited by 15
“We implement this behavior by using the Distributed Subgradient Method originally proposed in [10, 54, 55] for multi-agent environments.”
BackgroundMethodInfluentialZhang, J.-L., Qi, D., & Yu, M. (2014) · International Journal of Control Automation and Systems · doi:10.1007/s12555-013-0377-1 · Cited by 15
“…control problem takes on the general form: The well known distributed optimization algorithms, such as the gradient or gradient related methods [17,18], always have limited applicability because of local or overlapping information between agents and the inherent structure constraints of the…”
BackgroundTime-varying convex optimization for double-integrator dynamics over a directed network
Gong, P., Chen, F., & Lan, W. (2016) · Chinese Control Conference (CCC) · doi:10.1109/chicc.2016.7554519 · Cited by 15
Designing games for distributed optimization with a time varying communication graph
Li, N., & Marden, J. R. (2012) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2012.6426086 · Cited by 15
Distributed Coordination Load Shedding of Islanded Microgrids Based on Sub-Gradient Algorithm
Wu, X., Feng, S. L., & Jiang, P. (2017) · IEEE Access · doi:10.1109/access.2017.2725901 · Cited by 15
“Inspired by the decentralized droop control concept that exerts control through local frequency deviations without any communication [25] and the sub-gradient coordination algorithm of MAS that solves the optimization problem in a distributed way [26]–[28], a new fully distributed coordination load shedding (DCLS) is…”
BackgroundMethodGradient-free distributed optimization with exact convergence
Pang, Y., & Hu, G. (2022) · Automatica · doi:10.1016/j.automatica.2022.110474 · 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
“This random variation was first studied in [13] where to ensure the convergence, it was assumed that this sequence is doubly stochastic almost surely and i.”
BackgroundInfluentialWang, 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].”
MethodDecentralised Learning with Random Features and Distributed Gradient DescentPreprint
Richards, D., Rebeschini, P., & Rosasco, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.00360 · Cited by 22
“Many problems in decentralised multi-agent optimisation can be phrased as a form of consensus optimisation [46, 47, 19, 33, 32, 20, 27, 28, 7, 14, 43, 30].”
BackgroundCavalcante, R. L. G., Rogers, A., Jennings, N. R., & Yamada, I. (2011) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2011.2114325 · Cited by 17
Efficient Network Sharing With Asymmetric Constraint Information
Zhang, M., & Huang, J. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2927136 · Cited by 14
“15 Therefore, in addition to Algorithm 1, we can also adopt other algorithms (e.g. those from [44] and [45]).”
MethodConvergence Analysis of Distributed Gradient Descent Algorithms With One and Two Momentum Terms
Liu, B., Chai, L., & Yi, J. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3218663 · Cited by 16
“In line with these works, there has been a sustained research effort in developing algorithms for distributed optimization problems and many excellent results have been obtained; see [6], [7], [8], [9], [10], [11], [12], [13] and references therein.”
BackgroundMethodDistributed Quasi-Newton Method for Multi-Agent Optimization
Shorinwa, O., & Schwager, M. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3424436 · Cited by 15
“The simplest distributed optimization algorithms extend the well-known centralized gradient descent algorithm to the distributed setting [16], [17], using each agent’s local gradient.”
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
“The introduction of communication noise and errors on subgradients was addressed in [13], [17], while the case where the communication network is modeled as a random graph was treated in [9], [11].”
BackgroundLiu, C., Zhou, Z., Pei, J., Zhang, Y., & Shi, Y. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3209951 · Cited by 16
Distributed Inference Over Directed Networks: Performance Limits and Optimal Design
Bajović, D., Moura, J. M. F., Xavier, J., & Sinopoli, B. (2016) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2016.2543209 · Cited by 13
“, [35].”
Accelerated dual descent for constrained convex network flow optimization
Zarghamy, M., Ribeiro, A., & Jadbabaie, A. (2013) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2013.6760019 · Cited by 13
“Analysis of subgradient methods for convex optimization problems can be found in [7] and [8] with the latter taking into account uncertainty in the network structure.”
Proximal Alternating Direction Method of Multipliers for distributed optimization on weighted graphs
Meng, D., Fazel, M., & Mesbahi, M. (2015) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2015.7402406 · Cited by 15
“In contrast to subgradient type algorithms [12], [13], [14], [15], ADMM-type algorithms tend to achieve faster convergence rate which is highly preferred when local optimization at each node can be solved efficiently.”
Achieving Pareto Optimality through Distributed Learning
Young, H. P., Marden, J. R., & Pao, L. Y. (2024) · Oxford University Press eBooks · doi:10.1093/oso/9780198892908.003.0016 · Cited by 13
Diffusion 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…”
BackgroundHuang, Z., & Gong, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.07890 · Cited by 16
“…exist approaches for distributed optimization including distributed subgradient descent algorithms (Nedic et al., 2008; Nedic and Ozdaglar, 2009; Lobel and Ozdaglar, 2010), dual averaging methods (Duchi et al., 2011; Tsianos et al., 2012), and Alternating Direction Method of Multipliers (ADMM)…”
MethodRandomized Algorithms for Distributed Nonlinear Optimization Under Sparsity Constraints
Ravazzi, C., Fosson, S. M., & Magli, E. (2015) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2015.2500887 · Cited by 15
“everywhere, as often assumed in literature of distributed optimization [3], [4], [29], [30].”
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].”
MethodRandomized Block Proximal Methods for Distributed Stochastic Big-Data Optimization
Farina, F., & Notarstefano, G. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3027647 · Cited by 16
“In [16], consensus protocols were studied using random row-stochastic matrices, while in [18] a distributed subgradient method over random networks with underlying doubly stochastic matrices has been proposed.”
MethodGraph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient DescentPreprint
Richards, D., & Rebeschini, P. (2018) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.48550/arxiv.1809.06958 · Cited by 28
“…setting that we consider, which includes Johansson et al. (2007); Nedic and Ozdaglar (2009); Nedi´c et al. (2009); Johansson et al. (2009); Ram et al. (2010); Lobel and Ozdaglar (2011); Matei and Baras (2011); Boyd et al. (2011); Duchi et al. (2012); Shi et al. (2015); Mokhtari and Ribeiro (2016).”
BackgroundZeroth-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
A non-heuristic distributed algorithm for non-convex constrained optimization
Matei, I., & Baras, J. S. (2013) · University Libraries (University of Maryland) · Cited by 11
Distributed Optimization Over Networks
Nedić, A. (2018) · Lecture notes in mathematics · doi:10.1007/978-3-319-97142-1_1 · Cited by 13
Distributed load shedding for microgrid with compensation support via wireless network
Xu, Q., Yang, B., Chen, C., Lin, F., & Guan, X. (2018) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2017.1029 · Cited by 11
Distributed Linear Equations Over Random Networks
Yi, P., Lei, J., Chen, J., Hong, Y., & Shi, G. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3187379 · Cited by 12
“Hence, how network topology and connectivity affect the convergence and convergence rate of distributed computation has been an important research topic [5]–[8], and specifically, in distributed linear equations [9], [15], [26].”
BackgroundMethodInfluentialLiu, J., & Xie, J. F. (2020) · International Journal of Systems Science · doi:10.1080/00207721.2020.1820622 · Cited by 11
Su, B., & Wang, S. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.117516 · Cited by 13
Chen, F., Jin, J., Xiang, L., & Ren, W. (2021) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2021.3131678 · Cited by 12
“Oneclassofapproachesfordistributedoptimizationisdistributed subgradientdescent(DGD)[4],whichhasbeenextendedfromvar-iousperspectivestohandlediverserealisticissues,e.g.,noisyenvi-ronments[5],stochasticnetworks[6],andlinearornonlinearcon-straints[7],[8].”
Jiang, X., Zeng, X., Sun, J. Q., & Chen, J. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.2989835 · Cited by 11
“A large number of effective discretetime algorithms have been developed to solve distributed optimization problems in multi-agent networks, such as distributed gradient/subgradient methods [14], [17], [20], [21], [27].”
MethodDistributed Optimization in Power Networks and General Multi-agent Systems
Li, N. (2013) · CaltechTHESIS (California Institute of Technology) · doi:10.7907/nhvj-fx37 · Cited by 11
Optimal Output Agreement for T-S Fuzzy Multi-agent Systems: An Adaptive Distributed Approach
Li, J., Jin, Z., & Zhang, Y. (2023) · International Journal of Fuzzy Systems · doi:10.1007/s40815-023-01493-2 · Cited by 10
“And the subgradient method in [9] has been employed to cooperatively optimize a global objective function.”
BackgroundMethodDistributed Optimization With Personalization: A Flexible Algorithmic Framework
Huang, Y. T., Xu, J., Meng, W., Wai, H.-T., & Chai, L. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3381889 · Cited by 10
“Numerous distributed algorithms have been proposed to solve this problem over the last decade [11], [12], [13], [14], [15], [16].”
BackgroundSearch-Based Advertising Auctions With Choice-Based Budget Constraint
Choi, T., Li, X., & Ma, C. (2015) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2015.2394501 · Cited by 10
“Hence, we present an effective new approach to solve this problem (see [12], [16], [19]).”
MethodUbl, M., & Hale, M. (2021) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2021.3068372 · Cited by 10
“A representative sample of this work includes [7]–[12], and these algorithms all rely on an underlying averaging-based update law, i.”
BackgroundYi, P., & Li, L. (2021) · Journal of Systems Science and Complexity · doi:10.1007/s11424-020-0071-3 · Cited by 12
Lei, J., & Chen, H.-F. (2015) · Communications in Information and Systems · doi:10.4310/cis.2015.v15.n4.a1 · Cited by 9
“There exist many distributed problems that are solved by consensus-based distributed algorithms, for example, sensor localization [7], distributed optimization [8, 9], distributed stochastic approximation [10, 11], and distributed control [12][13].”
Background
Metadata
- Authors
- Lobel, I., & Ozdaglar, A.
- Affiliations
- New York University (US)
- Massachusetts Institute of Technology (US)
- Venue
- IEEE Transactions on Automatic Control
- Published
- 2011-06
- Volume
- 56
- Issue
- 6
- Pages
- 1291-1306
- ISSN
- 0018-9286 (ISSN-L)
- 1558-2523
- OpenAlex
- W2106901427
- Cited by
- 351
- References
- 28
- Citations by year
- 2026: 6 · 2025: 8 · 2024: 14 · 2023: 13 · 2022: 15 · 2021: 27 · 2020: 26 · 2019: 36 · 2018: 38 · 2017: 37 · 2016: 37 · 2015: 30 · 2014: 25 · 2013: 14 · 2012: 11
- FWCI
- 17.33
- 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 › Signal Processing › Sparse and Compressive Sensing Techniques
- Keywords
- convex optimization, multi-agent optimization, time-varying topology, random networks, link failure, averaging algorithms, almost sure convergence, cooperative 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.