Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
Open accessThe DOI matches its Crossref record; 89 of the 89 references it cites were found in a registry or an index; 10 of the 34 sources its claims cite were checked for support.
Abstract
This paper considers the problem of distributed optimization over time-varying graphs. For the case of undirected graphs, we introduce a distributed algorithm, referred to as DIGing, based on a combination of a distributed inexact gradient method and a gradient tracking technique. The DIGing algorithm uses doubly stochastic mixing matrices and employs fixed step-sizes and, yet, drives all the agents' iterates to a global and consensual minimizer. When the graphs are directed, in which case the implementation of doubly stochastic mixing matrices is unrealistic, we construct an algorithm that incorporates the push-sum protocol into the DIGing structure, thus obtaining the Push-DIGing algorithm. Push-DIGing uses column stochastic matrices and fixed step-sizes, but it still converges to a global and consensual minimizer. Under the strong convexity assumption, we prove that the algorithms converge at R-linear (geometric) rates as long as the step-sizes do not exceed some upper bounds. We establish explicit estimates for the convergence rates. When the graph is undirected it shows that DIGing scales polynomially in the number of agents. We also provide some numerical experiments to demonstrate the efficacy of the proposed algorithms and to validate our theoretical findings.
Overview
CoChat Summary
TL;DR
The paper introduces DIGing for distributed optimization over time-varying undirected graphs and Push-DIGing for time-varying directed graphs, both using fixed step-sizes and gradient tracking. Under strong convexity and smoothness, it proves global R-linear (geometric) convergence and gives explicit rate bounds.
Key findings
- DIGing uses doubly stochastic mixing matrices and fixed step-sizes; under Assumptions 1, 4, and 5, it converges to the unique optimum at a global R-linear rate \(O(\lambda^k)\) for step-sizes \(\alpha \in (0, 1.5(1-\delta)^2 \bar{\mu} J_1]\).
- Push-DIGing incorporates the push-sum protocol with column stochastic matrices and fixed step-sizes; under Assumptions 4–7, it also converges at a global R-linear rate \(O(\lambda^k)\) for \(\alpha \in (0, 1.5(1-\delta)^2 \bar{\mu} J_2]\).
- For undirected graphs, Corollary 11 gives iteration complexity \(O(\tau^{-2} B^3 n^{4.5} \bar{\kappa}^{1.5} \ln(1/\varepsilon))\), polynomial in the number of agents \(n\). For lazy Metropolis mixing on time-invariant connected undirected graphs, Corollary 12 gives rate \(\lambda = 1 - 1/(161312\, n^{4.5} \bar{\kappa}^{1.5})\) and iteration complexity \(O(n^{4.5} \bar{\kappa}^{1.5} \ln(1/\varepsilon))\).
- Numerical experiments with \(n=12\), \(m_i=1\), \(p=3\), and Huber loss show DIGing and variants have R-linear rates, while the push-gradient method has only sublinear rate; DIGing-ATC is faster in iterations than DIGing but has higher per-iteration communication cost, and Push-DIGing can be as fast as DIGing-ATC at half communication cost per iteration.
Methods
- The paper studies distributed convex optimization \(\min \sum_{i=1}^n f_i(x)\) over time-varying undirected and directed graphs, assuming smoothness with Lipschitz gradients and strong convexity of at least one local function.
- It proposes DIGing: \(x(k+1)=W(k)x(k)-\alpha y(k)\), \(y(k+1)=W(k)y(k)+\nabla f(x(k+1))-\nabla f(x(k))\), and Push-DIGing, which adds push-sum variables \(u,v,V\) and uses column stochastic matrices.
- Convergence analysis uses the small-gain theorem with an ergodic norm and a cycle of arrows \(q \to z \to \check{y} \to \check{x} \to q\); numerical experiments compare push-gradient, DIGing, DIGing-ATC, and Push-DIGing on time-invariant directed, time-varying undirected, and time-varying directed graphs.
Limitations
- The paper states an open question is obtaining improved estimates on convergence rates, especially scaling with the number of agents \(n\), and extensions to local constraints and couplings among agents.
- Step-size selection requires agents to agree on common upper bounds on \(n\) and \(B\), plus lower \(\bar{\mu}\) and upper \(L\); the paper assumes all agents use the same step-size, though it notes uncoordinated step-sizes are possible in subsequent work.
- The paper states its bounds on step-sizes are often conservative and uses hand-optimized step-sizes in experiments; the numerical experiments use a small network of \(n=12\), so the empirical validation is limited in scale.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
9 Valid · 0 Not valid · 10 Not checked · 37 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“This compares favorably to some of the existing literature, e.g., [70,76], which require detailed spectral information about the network for step-size selection.”
What the sources say
- Supportedcites [70] C. Xi and U. Khan, On the Linear Convergence of Distributed Optimization over Directed Graphs , preprint,arXiv:1510.02149, 2015. source
The part of the sentence this citation is offered for — that the cited work's step-size selection needs detailed spectral information about the network — is borne out by our copy: Theorem 1 (p. 13) sets α_min and α_max in terms of λ_min(M+M^⊤), d_- and d_∞, and the discussion after it (p. 14) states outright that 'the values of α and ᾱ need the knowledge of the network topology, which may not be available in a distributed manner,' flagging avoidance of that global knowledge as an open question. Section VI (p. 22) demonstrates the requirement in practice, computing λ_max/λ_min of H_i^⊤H_i, the degree constants and λ_min(M+M^⊤) to estimate the interval [9.6×10^-4, 0.26] before picking α = 0.1. The comparative framing ('compares favorably') is the citing authors' own conclusion and is not attributed to this source, so it is not judged here. (LLM, conf=0.85)
- Partly supportedcites [76] J. Zeng and W. Yin, ExtraPush for Convex Smooth Decentralized Optimization over Directed Networks , preprint,arXiv:1511.02942, 2015. sourceExperimental — accuracy not yet measured
Theorem 4 (p. 8) gives a condition on the step size, and the discussion on p. 9 relates the convergence bound to eigenvalues of network-derived matrices. But p. 9 calls the step-size condition sufficient, not necessary, and §6.1 (p. 12) selects step sizes by hand. The paper therefore supports a spectral dependence in its theoretical bound, not the categorical claim that step-size selection requires detailed spectral information. (LLM, conf=0.79)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Proposition 1 ( [62]). Assume null { I -W } = span { 1 } where W ∈ R n × n . If x ∗ satisfies conditions: (i) x ∗ = Wx ∗ (consensus), (ii) 1 ⊤ ∇ f ( x ∗ ) = 0 (optimality), then the rows of x ∗ are the same as each other and the transpose of each row is an optimal solution of the problem (1) .”
What the sources say
- Supportedcites [62] matched to “EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization” (2015) source
The paper’s discussion of Proposition 2.1 (p. 6) says that, under null{I−W} = span{1}, a point satisfying its consensus and optimality conditions has identical rows that solve problem (1.1). Lemma 3.1’s proof (p. 9) identifies 1ᵀ∇f(x*) = 0 as the optimality condition. The citing proposition paraphrases those conditions and conclusion. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“While the subgradient-push eliminates the requirement of graph balancing [22], it suffers from a slow sublinear 2 convergence rate even for strongly convex smooth functions due to its employment of diminishing step-size [41].”
What the sources say
- Supportedcites [41] A. Nedić and A. Olshevsky, Stochastic Gradient-Push for Strongly Convex Functions on Time-Varying Directed Graphs , preprint, arXiv:1406.2075, 2014. source
The paper reports an O((ln t)/t) rate for strongly convex functions with Lipschitz gradients using an appropriately chosen diminishing step-size (main-result passage; page unavailable). This is sublinear, although the Introduction and Conclusion emphasize that it improves on the earlier O((ln t)/√t) rate and is close to the best achievable rate in the noisy setting; “slow” is the citing authors’ characterization. (LLM, conf=0.85)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Assumption 2 is typical for many results in multi-agent coordination and distributed optimization [42]. It is much weaker than the assumption of every G un ( k ) being connected.”
What the sources say
- Supportedcites [42] matched to “Distributed Optimization Over Time-Varying Directed Graphs” (2015) source
In II. Problem, Algorithm and Main Results (p. 2), the paper calls its connectivity assumption typical and says it is considerably weaker than requiring each graph to be connected, because the necessary edges can appear over time. (LLM, conf=0.91)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“When the graph is undirected it shows that DIGing scales polynomially in the number of agents.”
- Also stated in: § ACHIEVING GEOMETRIC CONVERGENCE FOR DISTRIBUTED OPTIMIZATION OVER TIME-VARYING GRAPHS ∗ · p. 4 · plain
“Moreover, we show that the convergence rate of DIGing scales polynomially in the total number of agents in the network.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
- Also stated in: § ACHIEVING GEOMETRIC CONVERGENCE FOR DISTRIBUTED OPTIMIZATION OVER TIME-VARYING GRAPHS ∗ · p. 4 · plain
25 more claims
Create a free account to see all 56 claims and to verify the 2 references still open.
- It may state two separate claims as one. 13
- Probably not a substantial claim. 14
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Algorithm 2: Push-DIGing · p. 21
“N out i ( k ) is the set of agents that can receive the information from agent i (in-neighbors of agent i ) at time k .”
§ Algorithm 2: Push-DIGing · p. 21
“N out i ( k ) = { j ∣ ∣ ( - → i, j ) ∈ A ( k ) }”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Algorithm 1: DIGing · p. 10
“the gradients are close to zero in the neighborhood of the optimal point”
§ ACHIEVING GEOMETRIC CONVERGENCE FOR DISTRIBUTED OPTIMIZATION OVER TIME-VARYING GRAPHS ∗ · p. 5
“not necessarily a point where ∇ f i ( x ) = 0 ∀ i”
Citations
Cites
Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011) · Foundations and Trends® in Machine Learning · doi:10.1561/2200000016 · Cited by 17,075
Boyd, S. (2010) · now publishers, Inc. eBooks · doi:10.1561/9781601984616 · Cited by 12,677
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 2×
“References [60–62] use a difference structure to cancel the steady state error in decentralized gradient descent [47, 75], thereby developing the algorithm EXTRA and its proximal-gradient variant.”
MethodFast 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
Markov Chains and Mixing Times
Levin, D., Peres, Y., & Wilmer, E. (2008) · doi:10.1090/mbk/058 · Cited by 2,241
Distributed 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
Gossip-based computation of aggregate information
Kempe, D., Dobra, A., & Gehrke, J. (2004) · 44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings. · doi:10.1109/sfcs.2003.1238221 · Cited by 1,480 · cited 4×
“Instead, if every agent knows its out-degree, it is possible for the agents to construct a column stochastic matrix C and perform the following recursions with initialization u(0) = x(0) and v(0) = 1 to achieve the average (push-sum protocol [27]):”
BackgroundMethodInfluentialEXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
Shi, W., Ling, Q., Wu, G., & Yin, W. (2015) · SIAM Journal on Optimization · doi:10.1137/14096668x · Cited by 1,261
Self-citationDistributed 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
Self-citationDistributed average consensus with least-mean-square deviation
Xiao, L., Boyd, S., & Kim, S.-J. (2007) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2006.08.010 · Cited by 1,107 · cited 1×
“Some examples include distributed averaging [7,50,72], distributed spectrum sensing [1], formation control [49, 58], power system control [21, 55], statistical inference and learning [20, 45, 53].”
Background
Research works printed but not linked: 9
- Chen A., 2012, Allerton, 601
- Di Lorenzo P., 2015, Proceedings of the IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 229
- Forero P., 2010, J. Mach. Learn. Res., 59, 1663
- Mokhtari A., 2016, J. Mach. Learn. Res., 17, 1
- Nedić A., 2008, UK, 3
- A. Olshevsky, Efficient Information Aggregation Strategies for Distributed Control and Signal Processing , Ph.D. thesis, Massachusetts Institute of Technology, 2010.
- Rabbat M., 2004, New York, 20
- Ram S., 2009, Proceedings of INFOCOM, 3001
- Sayed A., 2013, New York, 323
Cited by
Items 201–300 of 1,070
Pin, L., Xiao, F., Wei, B., & Wang, A. (2021) · Systems & Control Letters · doi:10.1016/j.sysconle.2021.105002 · Cited by 26
Algorithm-Level Confidentiality for Average Consensus on Time-Varying Directed Graphs
Gao, H. B., & Wang, Y. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3140274 · Cited by 30
“Using the convergence definition in [43] and [54], we define the rate of convergence to be at least γ ∈ (0 , 1) if there exists a positive constant value C such that (cid:13)(cid:13) π ( k ) − ¯ x 0 1 (cid:13)(cid:13) ≤ Cγ k is true for all k , where π ( k ) = [ π 1 ( k ) , . . . , π N ( k )] T and ¯…”
BackgroundNetwork flows that solve least squares for linear equations
Liu, Y., Lou, Y., Anderson, B. D. O., & Shi, G. (2020) · Automatica · doi:10.1016/j.automatica.2020.109108 · Cited by 28
Falsone, A., & Prandini, M. (2023) · Automatica · doi:10.1016/j.automatica.2023.111269 · Cited by 29
Gradient-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 30
“Unlike the ergodic error estimates common in the existing literature [6, 10, 15, 16, 20], bound on the error between the objective function at the local estimate of the optimal solution, and the optimal value is provided at each iteration.”
BackgroundAn Accelerated Method For Decentralized Distributed Stochastic Optimization Over Time-Varying Graphs
Rogozin, A., Bochko, M., Dvurechensky, P. E., Gasnikov, A. V., & Lukoshkin, V. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683110 · Cited by 34
“Recently, development of such algorithms has become one of the main topics in optimization and machine learning motivated by large-scale learning problems with privacy constraints and other challenges such as data being produced or stored distribut-edly [13], [14], [15], [16], [17].”
BackgroundLi, H., Hu, J., Ran, L., Wang, Z., Lü, Q., Du, Z., & Huang, T. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3072373 · Cited by 28
“Some notable works, including EXTRA [20], Push-DIGing [21], and [22], study single separable smooth and convex objective functions.”
BackgroundMethodInfluentialAn Accelerated Decentralized Stochastic Proximal Algorithm for Finite SumsPreprint
Hendrikx, H., Bach, F., & Massoulié, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.11394 · Cited by 25
“…algorithms alternate rounds of computations (in which all nodes compute gradients with respect to their local data) and communications, in which nodes exchange information with their direct neighbors (Duchi et al., 2012; Shi et al., 2015; Nedic et al., 2017; Tang et al., 2018; He et al., 2018).”
BackgroundFeng, Y., Zhang, W., Xiong, J., Li, H., & Rutkowski, L. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2019.2963330 · Cited by 25
Improved distributed optimization algorithm and its application in energy saving of ethylene plant
Wang, T., Ye, Z., Wang, X., Li, Z., & Du, W. (2022) · Chemical Engineering Science · doi:10.1016/j.ces.2022.117449 · Cited by 24
Distributed Big-Data Optimization via Blockwise Gradient Tracking
Notarnicola, I., Sun, Y., Scutari, G., & Notarstefano, G. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3008713 · Cited by 26
“Primal-based distributed methods that converge to an exact consensual solution using fixed step-sizes are available in the literature; they can be roughly grouped as i) [20], [21]; ii) [22]–[24], iii) [9], [25]–[30]; and iv) [31]–[34].”
MethodCompressed Distributed Gradient Descent: Communication-Efficient Consensus over Networks
Zhang, X., Liu, J., Zhu, Z., & Bentley, E. S. (2019) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2019.8737489 · Cited by 27
“, achieving the same O(1/k) convergence rate with constant step-size [18] or even under time-varying network graphs [19]).”
BackgroundAn Optimal Algorithm for Decentralized Finite-Sum Optimization
Hendrikx, H., Bach, F., & Massoulié, L. (2021) · SIAM Journal on Optimization · doi:10.1137/20m134842x · Cited by 77
“In their synchronous versions, decentralized algorithms alternate rounds of computations (in which all nodes compute gradients with respect to their local data) and communications, in which nodes exchange information with their direct neighbors [11, 39, 27, 40].”
BackgroundMethodOptimal Algorithms for Distributed OptimizationPreprint
Uribe, C. A., Lee, S., Gasnikov, A. V., & Nedić, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.00232 · Cited by 40
Self-citationDecentralized Stochastic Gradient Tracking for Non-convex Empirical Risk MinimizationPreprint
Zhang, J., & You, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02712 · Cited by 54
“DSGT is inspired by DIGing [26, 29], which uses full gradients with a gradient tracking method, and achieves linear convergence rate for strongly convex and Lipschitz smooth objective functions.”
MethodInfluentialJiang, X., Zeng, X., Sun, J. Q., & Chen, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3170944 · Cited by 28
Li, X., Gao, Y., Chang, H., Huang, D., Ma, Y., Pan, R., Qi, H., Wang, F., Wu, S., Xu, K., et al. (2024) · Statistical Theory and Related Fields · doi:10.1080/24754269.2024.2343151 · Cited by 28
“Numerous studies have investigated the numerical convergence properties of the method (Blot et al., 2016; Lalitha et al., 2018; Lian et al., 2017; Nedic et al.,2017; Tang et al., 2018; Vanhaesebrouck et al., 2017).”
Multi/Single-Stage Sliding Manifold Approaches for Prescribed-Time Distributed Optimization
Zhou, S., Wei, Y., Cao, J., & Liu, Y. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3504355 · Cited by 27
“Numerous remarkable algorithms have been proposed for distributed optimization, e.g., gradient-descent-based methods [5], [6], [7], proportional-integral-based methods [8], [9], gradient tracking techniques [10], [11], [12], [13], and zero-gradient-sum (ZGS) algorithms [14], [15], [16].”
Towards Accelerated Rates for Distributed Optimization over Time-Varying Networks
Rogozin, A., Lukoshkin, V., Gasnikov, A. V., Kovalev, D. A., & Shulgin, E. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-91059-4_19 · Cited by 23
“Local steps may use gradient [6, 7, 8, 9, 10, 11, 12] or sub-gradient [13] computations.”
BackgroundMethodInfluentialByzantine-Resilient Decentralized Policy Evaluation With Linear Function Approximation
Wu, Z., Shen, H., Chen, T., & Ling, Q. H. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3090952 · Cited by 40
Distributed decision-coupled constrained optimization via Proximal-Tracking
Falsone, A., & Prandini, M. (2021) · Automatica · doi:10.1016/j.automatica.2021.109938 · Cited by 29
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
“Prominent first-order distributed optimization algorithms have been developed, including primal domain methods that combine classical (sub)gradient steps with local averaging, such as distributed subgradient methods [7], [8], first-order methods with historical gradients [9], distributed Nesterov gradient methods [10]…”
MethodMa, Q., Qin, J., Anderson, B. D. O., & Wang, L. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3245021 · Cited by 26
“Very recently, it has been found applicable to various interesting scenarios, for example, shortest path planning [10], distributed optimization algorithm design [11], and resilient estimation under attack over networks [12].”
BackgroundGeometric convergence of distributed gradient play in games with unconstrained action sets
Tatarenko, T., & Nedić, A. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.1501 · Cited by 23
“It is worth noting that all works on fast algorithms for distributed optimization have been presented for unconstrained problems, see Nedić et al. (2017); Shi et al.”
BackgroundInfluentialSelf-citationBin, M., Notarnicola, I., Marconi, L., & Notarstefano, G. (2019) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc40024.2019.9029824 · Cited by 23
Compressed Gradient Tracking Algorithm for Distributed Aggregative Optimization
Chen, L., Wen, G., Liu, H., Yu, W., & Cao, J. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3371876 · Cited by 26
“Assumptions 4 and 5 are standard assumptions for distributed optimizationproblemsontime-varyinggraphs(see[6]and[39]).”
BackgroundInfluentialResearch status and prospects of distributed collaborative optimization
Chai, T., & Yang, T. (2020) · Scientia Sinica Technologica · doi:10.1360/sst-2020-0040 · Cited by 23
Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function
Wang, L., & Liu, X. (2022) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2022.3182883 · Cited by 46
“EXTRA [32] and decentralized gradient tracking (DGT) algorithms [33]–[35] permit the use of a constant stepsize to attain an exact solution without sacrificing the convergence rate.”
MethodA Family of Distributed Momentum Methods Over Directed Graphs With Linear Convergence
Gao, J., Liu, X., Dai, Y., Huang, Y., & Yang, P. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3160684 · Cited by 24
“Some of them are developed (see [15]–[19]) by employing column-stochastic matrices and the push-sum consensus, others combine row-stochastic matrices with the push-sum consensus (see [20], [21]).”
BackgroundGuo, L., Shi, X., Cao, J., & Wang, Z. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3250839 · Cited by 27
“When gi = 0 and fi is strongly convex, several linear convergence algorithms have been proposed including D-ADMM [6], DLM [7], EXTRA [8], DIGing [9], Harnessing [10], AugDGM [11], [12], and Exact Diffusion [13].”
MethodDISA: A Dual Inexact Splitting Algorithm for Distributed Convex Composite Optimization
Guo, L., Shi, X., Yang, S., & Cao, J. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3301289 · Cited by 31
Maros, M., & Jaldén, J. (2019) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2019.2892055 · Cited by 26
An 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
Yi, X., Zhang, S., Yang, T., Chai, T., & Johansson, K. H. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.383 · Cited by 30
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
Achieving Linear Convergence in Distributed Aggregative Optimization Over Directed Graphs
Chen, L., Wen, G., Fang, X., Zhou, J., & Cao, J. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3382173 · Cited by 25
“The main difference is that, the local costs in [4], [5], [6], [7], [8], [9], [10], [11], [12], [14], [15], and [16] are dependent of only the agents’ own decision variables, while the local costs in problem (1) are dependent of not only the agents’ own decision variables, but also other agents’…”
BackgroundMethodInfluentialDistributed adaptive Newton methods with global superlinear convergence
Zhang, J., You, K., & Başar, T. (2022) · Automatica · doi:10.1016/j.automatica.2021.110156 · Cited by 31
“2015 al } As first-order methods (Shi et , Nedić et .”
BackgroundMethodInfluentialNonconvex Distributed Optimization via Lasalle and Singular Perturbations
Carnevale, G., & Notarstefano, G. (2022) · IEEE Control Systems Letters · doi:10.1109/lcsys.2022.3187918 · Cited by 21
Luan, M., Wen, G., Liu, H., Huang, T., Chen, G., & Yu, W. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3270185 · Cited by 28
“Moreover, it was proved that if the step sizes were suitably selected, the designed algorithms can attain a linear convergence rate in [21], [22], and [23].”
BackgroundMethodInfluentialAB /Push-Pull method for distributed optimization in time-varying directed networks
Nedić, A., Nguyen, D. T. A., & Nguyen, D. T. (2023) · Optimization methods & software · doi:10.1080/10556788.2023.2261602 · Cited by 42
“As discussed in [18], AB/Push-Pull allows for much larger value of the stepsize compared to Push-DIGing and it converges faster especially for ill-conditioned problems and when graphs are not well balanced.”
InfluentialSelf-citationA geometrically convergent method for distributed optimization over time-varying graphs
Nedić, A., Olshevsky, A., & Shi, W. (2016) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2016.7798402 · Cited by 25
Self-citationA Push-Pull Gradient Method for Distributed Optimization in NetworksPreprint
Pu, S., Shi, W., Xu, J., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.07588 · Cited by 21
“We test our proposed algorithm, Push-Pull, against Push-DIGing [22] and Xi-Row [24].”
BackgroundMethodInfluentialSelf-citationDecentralize and Randomize: Faster Algorithm for Wasserstein BarycentersPreprint
Dvurechensky, P. E., Dvinskikh, D., Gasnikov, A. V., Uribe, C. A., & Nedić, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.03915 · Cited by 81
“On the other hand, recent studies [34, 40, 37, 46, 31] on accelerated distributed convex optimization algorithms demonstrated their efficiency for convex optimization problems over arbitrary networks with inherently distributed data, i.”
BackgroundSelf-citationLi, H., Lin, Z., & Fang, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.04373 · Cited by 40
“In this paper, we extend two widely used decentralized algorithms of EXTRA (Shi et al., 2015) and DIGing (Nedić et al., 2017; Qu & Li, 2018), which have sparked a lot of interest in the distributed optimization community, to stochastic decentralized optimization by combining them with the powerful…”
BackgroundMethodInfluentialLinear Convergent Decentralized Optimization with CompressionPreprint
Liu, X., Li, Y., Wang, R., Tang, J., & Yan, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.00232 · Cited by 47
Local Exact-Diffusion for Decentralized Optimization and Learning
Alghunaim, S. A. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3383271 · Cited by 52
“…have introduced bias-correction algorithms resistant to local function heterogeneity, such as the alternating-direction-method-of-multipliers-based methods [31], [32], EXTRA [33], ED [12], [13] (also known as NIDS [34] and D 2 [35]), and gradient-tracking ( GT ) methods [36], [37], [38], [39].”
MethodADMM-Tracking Gradient for Distributed Optimization Over Asynchronous and Unreliable Networks
Carnevale, G., Bastianello, N., Notarstefano, G., & Carli, R. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3539454 · Cited by 32
“, N}, we randomly generate each matrix Qi so that all its eigenvalues belong to the interval [1, 5], while the components of each vector ri are randomly generated from the interval [−10, 20] with a uniform distribution.”
A distributed algorithm based on relaxed ADMM for energy resources coordination
Liu, H., Shi, Y., Wang, Z., Ran, L., Lü, Q., & Li, H. (2021) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2021.107482 · Cited by 22
Convergence 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
“After that Lü et al. [42] (time-varying unbalanced directed networks) and Nedic et al. [43] (undirected network), respectively, extended the work [39] to uncoordinated step-sizes.”
BackgroundMethodInfluentialDistributed Optimization With Event-Triggered Communication via Input Feedforward Passivity
Li, M., Su, L., & Liu, T. (2020) · IEEE Control Systems Letters · doi:10.1109/lcsys.2020.3001998 · Cited by 20
“, discrete-time algorithms [1]–[4] and continuous-time algorithms [5]–[8].”
InfluentialFully asynchronous policy evaluation in distributed reinforcement learning over networks
Sha, X., Zhang, J., You, K., Zhang, K., & Başar, T. (2021) · Automatica · doi:10.1016/j.automatica.2021.110092 · Cited by 32
Asynchronous Accelerated Proximal Stochastic Gradient for Strongly Convex Distributed Finite SumsPreprint
Hendrikx, H., Bach, F., & Massoulié, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09865 · Cited by 23
“In their synchronous versions, they alternate rounds of computations (in which all nodes compute gradients with respect to their local data) and communications in which nodes perform linear combinations of their freshly computed gradients with their neighbors (Shi et al., 2015; Nedic et al., 2017; Tang et al., 2018).”
BackgroundWei, M., Yu, W., Chen, D., Kang, M., & Cheng, G. (2025) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2024.124869 · Cited by 24
Distributed Personalized Gradient Tracking With Convex Parametric Models
Notarnicola, I., Simonetto, A., Farina, F., & Notarstefano, G. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3147007 · Cited by 20
Distributed 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
“In [13], two fast distributed gradient algorithms based on the centralized Nesterov gradient algorithm are proposed.”
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 24
“Recently, distributed gradient based methods with gradient tracking technique have been developed [47], [39], [50], [34].”
BackgroundMethodDistributed 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
Connectivity-Aware Semi-Decentralized Federated Learning over Time-Varying D2D Networks
Parasnis, R., Hosseinalipour, S., Chu, Y.-W., Chiang, M., & Brinton, C. G. (2023) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3565287.3610278 · Cited by 28
Chen, Y., & Yi, P. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3349774 · Cited by 22
“Assumption 2 is a typical setting for networked systems, cf., [33], [34].”
BackgroundChen, T.-Y., Chen, W., Wei, F.-F., Hu, X.-M., & Zhang, J. (2024) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2024.3380436 · Cited by 30
“For discrete-time optimization, representative algorithms are EXTRA (an exact first-order algorithm) [11], distributed proportional-integral algorithms [13], DIGing (distributed inexact gradient method and the gradient tracking technique) [9], and distributed Newton-Raphson algorithm [10].”
Qiu, Z., Liu, S., & Xie, L. (2018) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.4040 · Cited by 18
“Now, we combine (20) and (21) to obtain ?̃?(k) ≤ F(k)π(k) + α(k)1n ≤ F(k) ( I − L̃(k − 1) ) ?̃?(k − 1) + α(k)1n, (22)”
Optimal Distributed Convex Optimization on Slowly Time-Varying Graphs
Rogozin, A., Uribe, C. A., Gasnikov, A. V., Malkovsky, N., & Nedic, A. (2019) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2019.2949439 · Cited by 29
“Particularly, we consider PANDA [22], DIGing [7] and Nesterov method for static networks Acc-DNGD [9].”
BackgroundMethodResultInfluentialDistributed Nash Equilibrium Seeking for Multiple Coalition Games by Coalition Estimate Strategies
Wang, D., Liu, J., Lian, J., Dong, X., & Wang, W. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3385311 · Cited by 19
“Moreover, when the communication topology is depicted by a double stochastic matrix, (27) can be further changed into the DIG-ing algorithm [23], [24].”
BackgroundDecentralized 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 19
Self-citationA Computation-Efficient Decentralized Algorithm for Composite Constrained Optimization
Lü, Q., Liao, X., Li, H., & Huang, T. (2020) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2020.3037837 · Cited by 23
Chen, Y., Hashemi, A., & Vikalo, H. (2021) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2021.3133372 · Cited by 23
“3 Remark 2: Assumption 1(a) is readily satisfied for a variety of graph structures such as the B-strongly connected directed graph introduced in [7], i.”
BackgroundMethodResultInfluentialWang, Y., Liu, S., Sun, B. N., & Li, X. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3143157 · Cited by 20
“Remark 4: In recent years, quite a few researches [36]–[38] on ED problem are conducted with the aid of EXTRA and Push-DIGing [35] algorithms in undirected and directed graphs respectively with a fixed stepsize, respectively.”
BackgroundMethodInfluentialThe Gradient Tracking Is a Distributed Integral Action
Notarnicola, I., Bin, M., Marconi, L., & Notarstefano, G. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3248487 · Cited by 23
“See, for instance, [3], [4], [5], [6], [7], [8], [9], [10], [11], [12].”
BackgroundMethodInfluentialLiu, H., Yu, W., Zheng, W. X., Nedić, A., & Zhu, Y. (2023) · Automatica · doi:10.1016/j.automatica.2023.111346 · Cited by 24
Self-citationDifferentially private distributed online optimization via push-sum one-point bandit dual averaging
Zhao, Z., Yang, J., Gao, W., Wang, Y., & Wei, M. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127184 · Cited by 17
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
“Finally, the gradient tracking mechanism has a large expansion value, for many centralized or distributed gradient-based optimization algorithms, the gradient tracking mechanism can be applied to obtain the corresponding distributed algorithms based on gradient tracking [25].”
MethodInfluentialDistributed nonconvex optimization for sparse representation
Sun, Y., & Scutari, G. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952916 · Cited by 18
Partition-based multi-agent optimization in the presence of lossy and asynchronous communication
Todescato, M., Bof, N., Cavraro, G., Carli, R., & Schenato, L. (2019) · Automatica · doi:10.1016/j.automatica.2019.108648 · Cited by 19
On the convergence of event-triggered distributed algorithm for economic dispatch problem
Zhang, K., Xiong, J., Dai, X., & Lü, Q. (2020) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2020.106159 · Cited by 18
Convergence analysis of a distributed gradient algorithm for economic dispatch in smart grids
Zhang, H., Liang, S., Jing, L., & Han, Y. (2021) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2021.107373 · Cited by 19
A Geometrically Converging Dual Method for Distributed Optimization Over Time-Varying Graphs
Maros, M., & Jaldén, J. (2020) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2020.3018743 · Cited by 21
“By proposing a different error correction scheme than [15], [16] the authors of [21] proposed decentralized inexact gradient tracking (DIGing), a method that converges linearly to the optimal solution even if the undirected graph is time-varying.”
BackgroundMethodInfluentialOn the geometric convergence rate of distributed economic dispatch/demand response in power networksPreprint
Doan, T. T., & Olshevsky, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.06660 · Cited by 18
Self-citationDecentralized Multi-Agent Reinforcement Learning with Networked Agents: Recent AdvancesPreprint
Zhang, K., Yang, Z., & Başar, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.03821 · Cited by 18
Accelerated Distributed Aggregative Optimization
Liu, J., Chen, S., Cai, S., Xu, C., & Chu, J. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3546096 · Cited by 24
“To deal with the issues of slow convergence rate and non-optimal solution, the gradient tracking strategy is merged with the distributed convex optimization algorithms where an estimate of the global average gradient is used to replace the local gradient in each agent [12], [13].”
MethodOptimal gradient tracking for decentralized optimization
Song, Z., Shi, L., Pu, S., & Yan, M. (2023) · Mathematical Programming · doi:10.1007/s10107-023-01997-7 · Cited by 62
“GT [9, 10, 32, 37, 59] O (( κ+ 1 θ2 ) log 1 ǫ ) O (( κ+ 1 θ2 ) log 1 ǫ ) !”
BackgroundMethodInfluentialA Unified Distributed Method for Constrained Networked Optimization via Saddle-Point Dynamics
Huang, Y., Meng, Z., Sun, J. Q., et al. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3327940 · Cited by 17
Wang, Y., & Nedić, A. (2023) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3348158 · Cited by 28
“Typical examples include gradient-tracking-based algorithms such as Aug-DGM [8], DIGing [14], AsynDGM [15], AB [9], Push-Pull [16], [17], and ADD-OPT [18], etc.”
MethodInfluentialSelf-citationOn the Performance of Gradient Tracking with Local Updates
Nguyen, E. D. H., Alghunaim, S. A., Yuan, K., & Uribe, C. A. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10383873 · Cited by 41
“Among the most prolific include decentralized/distributed gradient descent (DGD) [1], [2], EX-TRA [3], Exact-Diffusion/D 2 /NIDS (ED) [4]–[7], and Gradient Tracking (GT) [8]–[11].”
BackgroundYan, Z., & Li, D. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3362143 · Cited by 22
“Therefore, the mixing weights matrix with the erroneous communication can be denoted as a random matrix, and the graph of DFL system is a time-varying graph [42], [43], [44].”
BackgroundPrivacy-Preserving Push-Pull Method for Decentralized Optimization via State Decomposition
Cheng, H., Liao, X., Li, H., Lü, Q., & Zhao, Y. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3402430 · Cited by 25
“Representative algorithms include AugDGM [7], AsynDGM [8], DIGing [9], [10], Push-DIGing [10], ADD-Opt [11], SONATA [11]/NEXT [13], ASY-SONATA [14], AB [15], TV-AB [16], [17] and Push-Pull [18], [19], [20], which can attain an R -linear 1 convergence rate.”
BackgroundMethodInfluentialRandom 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
“For time-varying unbalanced directed networks, [19], [20] designed algorithms by incorporating the so-called push-sum protocol and gradient descent method.”
BackgroundMethodA non-cooperative game-based distributed optimization method for chiller plant control
Li, S., Pan, Y., Wang, Q., et al. (2021) · Building Simulation · doi:10.1007/s12273-021-0869-5 · Cited by 17
“2019), and gradient tracking method (Nedić et al. 2017) have recently found wide application in a number of areas.”
MethodDistributed Nonconvex Multiagent Optimization Over Time-Varying NetworksPreprint
Sun, Y., Scutari, G., & Palomar, D. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.00249 · Cited by 17
“In the same technical report [26], the authors proposed pushDIGing, the extension of DIGing to B-strongly connected digraphs.”
BackgroundMethodInfluentialAsynchronous Subgradient-Push.Preprint
Assran, M., & Rabbat, M. (2018) · arXiv (Cornell University) · Cited by 19
Fully Asynchronous Distributed Optimization with Linear Convergence in Directed NetworksPreprint
Zhang, J., & You, K. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08215 · Cited by 43
“It then follows from (11) that YV(k + 1) = B̃V(k)YV(k) + V (k + 1) †R(k) (33) where B̃V(k) = V (k + 1)†B̃(k)V (k) and one can prove that each row except the i-th (i ∈ IV(k)) row of B̃V(k) has row sum 1 using a similar arguments as in the Lemma 4 of [32] and [27].”
BackgroundMethodInfluentialGao, J., Liu, X., Dai, Y., Huang, Y., & Gu, J. (2022) · Computational Optimization and Applications · doi:10.1007/s10589-022-00432-5 · Cited by 25
“…focusing on convex optimization have been developed, including the distributed gradient descent (DGD) [13, 14], distributed gradient methods with momentum [15, 16], gradient-tracking based methods [17–20], gradient-tracking based methods with momentum [21–26] and primal-dual based methods [27, 28].”
MethodFast Coordination of Distributed Energy Resources Over Time-Varying Communication Networks
Zholbaryssov, M., Hadjicostis, C. N., & Domínguez-García, A. D. (2022) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2022.3213626 · Cited by 23
“Since R̃[k] is row-stochastic [19], the following relations hold:”
BackgroundMethodInfluentialToward a Systems Theory of Algorithms
Dörfler, F., He, Z., Belgioioso, G., Bolognani, S., Lygeros, J., & Muehlebach, M. (2024) · IEEE Control Systems Letters · doi:10.1109/lcsys.2024.3406943 · Cited by 41
“A system-theoretic interpretation of the gradient-tracking algorithm [58] as a feedback interconnection between the gradient descent dynamics and a dynamic average consensus protocol [57].”
BackgroundInfluentialAccelerated distributed Nesterov Gradient Descent for convex and smooth functions
Qu, G., & Li, N. (2017) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2017.8263979 · Cited by 19
Tutorial on Dynamic Average Consensus: The Problem, Its Applications, and the Algorithms
Kia, S. S., Scoy, B. V., Cortés, J., Freeman, R. A., Lynch, K., & Martínez, S. (2019) · IEEE Control Systems · doi:10.1109/mcs.2019.2900783 · Cited by 449
Exact Diffusion for Distributed Optimization and Learning --- Part I: Algorithm DevelopmentPreprint
Yuan, K., Ying, B., Zhao, X., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05122 · Cited by 16
Achieving Linear Convergence in Distributed Asynchronous Multi-agent OptimizationPreprint
Tian, Y., Sun, Y., & Scutari, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10359 · Cited by 16
“The key result is a generalization of the small gain theorem (cf. Theorem 22), first used in [35].”
BackgroundMethodInfluentialA Fully Distributed Hybrid Control Framework For Non-Differentiable Multi-Agent Optimization
Jiang, X., Zeng, X., Sun, J. Q., Chen, J., & Wei, Y. (2022) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2022.105872 · Cited by 15
Ji, L., Shen, M., Yang, S., et al. (2022) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2022.108601 · Cited by 15
Game-theoretical approach for task allocation problems with constraints
Liu, C. L., Lu, K., Chen, X., & Szolnoki, A. (2023) · Applied Mathematics and Computation · doi:10.1016/j.amc.2023.128251 · Cited by 15
“Indeed, the related problems can be solved by minimizing the global objective function in a multi-agent system, where each individual can only obtain the information of its adjacent neighbors in a connected graph [9, 10, 11, 12, 13].”
Background
Metadata
- Authors
- Nedić, A., Olshevsky, A., & Shi, W.
- Affiliations
- Boston University (US)
- Arizona State University (US)
- Venue
- SIAM Journal on Optimization
- Published
- 2017-01
- Volume
- 27
- Issue
- 4
- Pages
- 2597-2633
- ISSN
- 1052-6234 (ISSN-L)
- 1095-7189
- OpenAlex
- W2963649943
- Cited by
- 1,069
- References
- 38
- Citations by year
- 2026: 95 · 2025: 147 · 2024: 130 · 2023: 124 · 2022: 118 · 2021: 114 · 2020: 138 · 2019: 106 · 2018: 64 · 2017: 29
- FWCI
- 46.51
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- SIAM Journal on Optimization (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- U.S. Air Force (AF FA95501510394)
- Office of Naval Research (N00014-12-1-0998)
- National Science Foundation (CNS 15-44953)
- 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, dynamic graphs, geometric convergence, R-linear convergence, gradient tracking, strong convexity, fixed step size, undirected graphs, directed graphs
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
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.