Augmented distributed gradient methods for multi-agent optimization under uncoordinated constant stepsizes
The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
We consider distributed optimization problems in which a number of agents are to seek the optimum of a global objective function through merely local information sharing. The problem arises in various application domains, such as resource allocation, sensor fusion and distributed learning. In particular, we are interested in scenarios where agents use uncoordinated (different) constant stepsizes for local optimization. According to most existing works, using this kind of stepsize rule for update, which is necessary in asynchronous scenarios, will lead to some gap (error) between the estimated result and the exact optimum. To deal with this issue, we develop a new augmented distributed gradient method (termed Aug-DGM) based on consensus theory. The proposed algorithm not only allows for using uncoordinated stepsizes but also, most importantly, be able to seek the exact optimum even with constant stepsizes assuming that the global objective function has Lipschitz gradient. A simple numerical example is provided to illustrate the effectiveness of the algorithm.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The algorithm we will study in this paper crucially relies on tracking differences of gradients and is a minor variation of algorithms that have appeared in [73,74] and [15-17].”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [74]
In the citing paper
“However, none of the papers mentioned in this paragraph provide a theoretical analysis for strongly convex optimization problems over time-varying graphs , which is the goal of this paper.”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [74]
In the citing paper
“Allowing the agents to use uncoordinated (different) stepsizes (all satisfying an upper bound) is possible; see our very recent subsequent work [44] as well as the related papers [31,74].”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [74]
In the citing paper
“We also find that when the graph is well connected, the ATC strategy employed in Aug-DGM can improve the linear rate.”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [74]
Citations
Cites
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,677
Consensus and Cooperation in Networked Multi-Agent Systems
Olfati-Saber, R., Fax, J. A., & Murray, R. M. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2006.887293 · Cited by 10,522 · cited 1×
“In the context of distributed computation, consensus theory is particularly suitable for distributed implementation of algorithms as it allows agents to obtain global results by merely taking local actions [8].”
BackgroundFast linear iterations for distributed averaging
Xiao, L., & Boyd, S. (2004) · Systems & Control Letters · doi:10.1016/j.sysconle.2004.02.022 · Cited by 2,706
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×
“Some extension has also been made for cases under constraints [11], [12], cases where only noisy gradient is available [13], [14] and directed graphs [15].”
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
Distributed Optimization Over Time-Varying Directed Graphs
Nedic, A., & Olshevsky, A. (2015) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2364096 · Cited by 1,187
Distributed optimization in sensor networks
Rabbat, M., & Nowak, R. (2004) · Proceedings of the 3rd international symposium on Information processing in sensor networks · doi:10.1145/984622.984626 · Cited by 901 · cited 1×
“Distributed optimization has received a renewed attention from the control and machine learning communities due to its wide applications in areas such as formation control [1], resource allocation [2], sensor fusion in wireless sensor networks [3]–[5] and distributed learning [6] and just to name a few.”
BackgroundDual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
Duchi, J. C., Agarwal, A., & Wainwright, M. J. (2010) · Cited by 884
Distributed Continuous-Time Convex Optimization on Weight-Balanced Digraphs
Gharesifard, B., & Cortes, J. (2014) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2013.2278132 · Cited by 833 · cited 2×
“where θ ∈ R is the global variable to be optimized, which is equivalent to solve the following problem [28]”
ResultOn Distributed Convex Optimization Under Inequality and Equality Constraints
Zhu, M., & Martinez, S. (2012) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2011.2167817 · Cited by 759 · cited 1×
“Some extension has also been made for cases under constraints [11], [12], cases where only noisy gradient is available [13], [14] and directed graphs [15].”
BackgroundDiffusion Adaptation Strategies for Distributed Optimization and Learning Over Networks
Chen, J., & Sayed, A. H. (2012) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2012.2198470 · Cited by 680
Fast Distributed Gradient Methods
Jakovetic, D., Xavier, J., & Moura, J. M. F. (2014) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2298712 · Cited by 624 · cited 2×
“Note that our assumption is similar with [7] and [14] except for that we drop the strongly convex assumption but it is quite different from most (sub)gradient-based methods [9], [25], [26] where 2015 IEEE 54th Annual Conference on Decision and Control (CDC) December 15-18, 2015.”
ResultSimultaneous Routing and Resource Allocation Via Dual Decomposition
Xiao, L., Johansson, M., & Boyd, S. P. (2004) · IEEE Transactions on Communications · doi:10.1109/tcomm.2004.831346 · Cited by 561 · cited 1×
“Distributed optimization has received a renewed attention from the control and machine learning communities due to its wide applications in areas such as formation control [1], resource allocation [2], sensor fusion in wireless sensor networks [3]–[5] and distributed learning [6] and just to name a few.”
BackgroundDiscrete-time dynamic average consensus
Zhu, M., & Martínez, S. (2010) · Automatica · doi:10.1016/j.automatica.2009.10.021 · Cited by 488 · cited 2×
“Lemma 1 (Conservation Property [30]): Let ḡ(k) = 11 m g(x(k)), y(0) = g(x(0)), then ȳ(k) = ḡ(k),∀k ≥ 0.”
A control perspective for centralized and distributed convex optimization
Wang, J., & Elia, N. (2011) · IEEE Conference on Decision and Control and European Control Conference · doi:10.1109/cdc.2011.6161503 · Cited by 398
Distributed Alternating Direction Method of Multipliers
Wei, E., & Ozdaglar, A. (2012) · 2012 IEEE 51st IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2012.6425904 · Cited by 389 · cited 1×
“Building on this method, distributed versions of Alternative Direction Method of Multipliers (ADMM [18]) have been proposed for solving the above same problem [19], [20].”
MethodD-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization
Mota, J. F. C., Xavier, J. M. F., Aguiar, P. M. Q., & Puschel, M. (2013) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2013.2254478 · Cited by 363 · cited 1×
“Building on this method, distributed versions of Alternative Direction Method of Multipliers (ADMM [18]) have been proposed for solving the above same problem [19], [20].”
MethodDistributed Asynchronous Constrained Stochastic Optimization
Srivastava, K., & Nedic, A. (2011) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2011.2118740 · Cited by 350 · cited 1×
“Some extension has also been made for cases under constraints [11], [12], cases where only noisy gradient is available [13], [14] and directed graphs [15].”
Background1Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed GraphsPreprint
Nedić, A., & Olshevsky, A. (2016) · Cited by 316
Asynchronous Broadcast-Based Convex Optimization Over a Network
Nedic, A. (2011) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2010.2079650 · Cited by 310 · cited 2×
“In [21], an asynchronous broadcast-based algorithm is designed to handle the problem of random link failures as well as uncoordinated update over random networks.”
MethodDistributed optimization for cooperative agents: application to formation flight
Raffard, R. L., Tomlin, C. J., & Boyd, S. P. (2004) · 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601) · doi:10.1109/cdc.2004.1428778 · Cited by 245 · cited 1×
“Distributed optimization has received a renewed attention from the control and machine learning communities due to its wide applications in areas such as formation control [1], resource allocation [2], sensor fusion in wireless sensor networks [3]–[5] and distributed learning [6] and just to name a few.”
BackgroundDistributed Optimal Consensus Filter for Target Tracking in Heterogeneous Sensor Networks
Zhu, S., Chen, C., Li, W., Yang, B., & Guan, X. (2013) · IEEE Transactions on Cybernetics · doi:10.1109/tsmcb.2012.2236647 · Cited by 184 · cited 1×
“Distributed optimization has received a renewed attention from the control and machine learning communities due to its wide applications in areas such as formation control [1], resource allocation [2], sensor fusion in wireless sensor networks [3]–[5] and distributed learning [6] and just to name a few.”
BackgroundSelf-citationDecentralized Multi-Agent Optimization via Dual Decomposition
Terelius, H., Topcu, U., & Murray, R. M. (2011) · IFAC Proceedings Volumes · doi:10.3182/20110828-6-it-1002.01959 · Cited by 147 · cited 1×
“On the other hand, dual decomposition is widely employed to solve large-scale optimization problems which are separable in the dual domain [16], [17].”
BackgroundA Collaborative Training Algorithm for Distributed Learning
Predd, J. B., Kulkarni, S. R., & Poor, H. V. (2009) · IEEE Transactions on Information Theory · doi:10.1109/tit.2009.2012992 · Cited by 147 · cited 1×
“Distributed optimization has received a renewed attention from the control and machine learning communities due to its wide applications in areas such as formation control [1], resource allocation [2], sensor fusion in wireless sensor networks [3]–[5] and distributed learning [6] and just to name a few.”
BackgroundNewton-Raphson consensus for distributed convex optimization
Zanella, F., Varagnolo, D., Cenedese, A., Pillonetto, G., & Schenato, L. (2011) · IEEE Conference on Decision and Control and European Control Conference · doi:10.1109/cdc.2011.6160605 · Cited by 96
Asynchronous Gossip Algorithm for Stochastic Optimization: Constant Stepsize Analysis*
Ram, S. S., Nedić, A., & Veeravalli, V. V. (2010) · Springer eBooks · doi:10.1007/978-3-642-12598-0_5 · Cited by 55 · cited 1×
“This is analogous to using different stepsizes in the average sense especially when it comes to random networks [21], [22].”
MethodAsynchronous Newton-Raphson Consensus for Distributed Convex Optimization
Zanella, F., Varagnolo, D., Cenedese, A., Pillonetto, G., & Luca Schenato, B. (2012) · IFAC Proceedings Volumes · doi:10.3182/20120914-2-us-4030.00027 · Cited by 40 · cited 1×
“Specifically, a distributed Newton-Raphson algorithm is proposed in [23], [24] and the convergence properties of its asynchronous computation is investigated which requires the cost function to be continuous up to the second derivatives.”
Background
Cited by
Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
Nedić, A., Olshevsky, A., & Shi, W. (2017) · SIAM Journal on Optimization · doi:10.1137/16m1084316 · Cited by 1,069
“The algorithm we will study in this paper crucially relies on tracking differences of gradients and is a minor variation of algorithms that have appeared in [73,74] and [15–17].”
MethodInfluentialA survey of distributed optimization
Yang, T., Yi, X., Wu, J., Yuan, Y., Wu, D., Meng, Z., Hong, Y., Wang, H., Lin, Z., & Johansson, K. H. (2019) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2019.05.006 · Cited by 913
“…based on the combination of the d istributed i nexact g radient method and the gradient track ing technique (abbreviated as DIGing), developed independently in Nedi ´c et al. (2017a) ; Qu and Li (2018) ; Xu, Zhu, Soh, and Xie (2015, 2018a) and Nedi ´c, Olshevsky, Shi, and Uribe (2017b) .”
MethodHarnessing Smoothness to Accelerate Distributed Optimization
Qu, G., & Li, N. (2018) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2017.2698261 · Cited by 565
“Paper [24] focuses on uncoordinated step sizes.”
Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization
Nedic, A., Olshevsky, A., & Rabbat, M. G. (2018) · Proceedings of the IEEE · doi:10.1109/jproc.2018.2817461 · Cited by 534
Tutorial on dynamic average consensus: the problem, its applications,\n and the algorithms
Kia, S. S., Scoy, B. V., Cortés, J., Freeman, R. A., Lynch, K., & Martı́nez, S. (2018) · eScholarship (California Digital Library) · Cited by 404
Metadata
- Authors
- Xu, J., Zhu, S., Soh, Y. C., & Xie, L.
- Affiliations
- Nanyang Technological University (SG)
- Venue
- 2015 54th IEEE Conference on Decision and Control (CDC)
- Publisher
- IEEE
- Published
- 2015-12
- Pages
- 2055-2060
- ISSN
- 0191-2216 (ISSN-L)
- OpenAlex
- W2291434103
- Cited by
- 332
- References
- 27
- Citations by year
- 2026: 12 · 2025: 37 · 2024: 43 · 2023: 40 · 2022: 35 · 2021: 37 · 2020: 46 · 2019: 39 · 2018: 28 · 2017: 11 · 2016: 4
- FWCI
- 10.65
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Conference on Decision and Control (CDC) (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 optimization, multi-agent systems, consensus algorithms, Lipschitz gradient, asynchronous optimization, local information sharing
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.