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 501–600 of 1,070
On the Divergence of Decentralized Nonconvex Optimization
Hong, M., Zeng, S., Zhang, J., & Sun, H. (2022) · SIAM Journal on Optimization · doi:10.1137/20m1353149 · Cited by 9
“To guarantee convergence of DGD to a stationary solution, it needs the (LLB) condition, and that the stepsize satisfies ([9, Theorem 2]): A closely related family of algorithms are called the Gradient Tracking (GT) algorithms [10, 11, 12], which uses constant stepsizes.”
MethodInfluentialAutomated Worst-Case Performance Analysis of Decentralized Gradient Descent
Colla, S., & Hendrickx, J. M. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683505 · Cited by 8
“While we focus on DGD in section IV, this form of communication is used in many other decentralized methods such as EXTRA [3], DIGing [4], NIDS [5] and the results presented in this section can be exploited for all these methods too.”
MethodDistributed convex optimization via proportional-integral-differential algorithm
Zhu, W. Q., & Tian, H. (2021) · Measurement and Control · doi:10.1177/00202940211029332 · Cited by 6
“Noticing (11), by the variation of parameter formula, we have”
BackgroundTime-varying constrained proximal type dynamics in multi-agent network games
Cenedese, C., Belgioioso, G., Grammatico, S., et al. (2020) · European Control Conference (ECC) · doi:10.23919/ecc51009.2020.9143683 · Cited by 6
“In the past years, several results were proposed for optimization problems subject to a time-varying communication network: in [11] the subgradients of the cost functions are bounded and the communication is described by a strongly connected sequence of directed graphs, while in [12] the cost functions are assumed to…”
BackgroundHybrid Voltage Control in Distribution Networks Under Limited Communication RatesPreprint
Liu, H. J., Shi, W., & Zhu, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.07094 · Cited by 6
Self-citationExact Diffusion for Distributed Optimization and Learning --- Part II: Convergence AnalysisPreprint
Yuan, K., Ying, B., Zhao, X., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.05142 · Cited by 6
Distributed Zero-Order Algorithms for Nonconvex Multi-Agent OptimizationPreprint
Tang, Y., Zhang, J., & Li, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11444 · Cited by 5
“gradient tracking O ( 1 t ) [14] O ([ 1− c(1−ρ)(2) (μ L )3 2 ]t) [4] (convex)”
MethodRate of Convergence for Distributed Optimization with Uncertain CommunicationsPreprint
Rezaeinia, P., & Gharesifard, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.10342 · Cited by 7
“This selective participation differentiates an effective communication network graph from conventional network graphs that do not filter connections based on these criteria.”
A Survey of Distributed Optimization Methods for Multi-Robot SystemsPreprint
Halsted, T., Shorinwa, O., Yu, J., & Schwager, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12840 · Cited by 71
“The distributed subgradient methods ([11], [10], [12], [37]”
MethodXin, R., Das, S., Khan, U. A., & Kar, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.01594 · Cited by 30
“To address this issue, stochastic methods that are robust to heterogeneous data have been proposed, e.g., D2 [51] that is derived from primal-dual formulations [22,25,47,69] and GT-DSGD [29,63] that is based on gradient tracking [10,33,38,41,67].”
MethodZhang, Y., Zhang, Y., Liu, Z., & Chen, Z. (2025) · Science China Information Sciences · doi:10.1007/s11432-024-4140-5 · Cited by 7
A Stochastic Gradient Tracking Algorithm for Decentralized Optimization With Inexact Communication
Shah, S. M., & Bollapragada, R. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3548470 · Cited by 7
“3) To validate our theoretical results, we report experimental results that compare IC-GT with similar methods like DGD [1], DIGing [7], and EXTRA [6].”
InfluentialA stochastic gradient tracking algorithm with adaptive momentum for distributed optimization
Li, Y., Hu, H., Zhang, K., Lü, Q., Deng, S., & Li, H. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130095 · Cited by 5
Xu, L., Yi, X., Sun, J., Shi, Y., Johansson, K. H., & Yang, T. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3563431 · Cited by 11
“In this section, we propose a DGTA with quantized communication by integrating the DGTA [40], [41] with the encoder–decoder scheme.”
InfluentialDistributed convex optimization as a tool for solving f -consensus problems
Huang, C., Anderson, B. D. O., Zhang, H., et al. (2023) · Automatica · doi:10.1016/j.automatica.2023.111087 · Cited by 5
Decentralized Multitask Online Convex Optimization Under Random Link Failures
Yan, W., & Cao, X. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3348954 · Cited by 8
“Convergence of the resulting algo-rithm can be analyzed by referring to techniques developed for decentralized optimization under time-varying networks [27].”
MethodYuan, R., Zhao, Z., Chen, S., & Chai, T. (2024) · International Journal of Robust and Nonlinear Control · doi:10.1002/rnc.7336 · Cited by 6
Distributed optimisation algorithm based on iterative learning control
Dong, X., Zhang, R., Chen, X., & Xue, L. (2024) · International Journal of Systems Science · doi:10.1080/00207721.2024.2388810 · Cited by 5
“In other words, the distributed optimisation algorithm does not necessarily fail due to local failures. including distributed Extra and DIGing algorithms, have also been provided in Nedić et al. (2017) and Shi et al. (2015).”
Taming Subnet-Drift in D2D-Enabled Fog Learning: A Hierarchical Gradient Tracking Approach
Chen, E., Wang, S., & Brinton, C. G. (2024) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom52122.2024.10621133 · Cited by 12
A Method for Transforming Non-Convex Optimization Problem to Distributed Form
Khamisov, O. O., Khamisov, O. V., Ganchev, T. D., & Semenkin, E. S. (2024) · Mathematics · doi:10.3390/math12172796 · Cited by 6
“Namely, application in optimal transport [13] including coordination of mobile autonomous agents [14,15] and railway traffic [16,17], power systems control [18,19] with demand response [20] as well as data analysis in sensor networks [21,21].”
BackgroundStatistical inference for decentralized federated learning
Gu, J., & Chen, S. X. (2024) · The Annals of Statistics · doi:10.1214/24-aos2452 · Cited by 12
Distributed ADMM With Linear Updates Over Directed Networks
Rokade, K., & Kalaimani, R. K. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3529703 · Cited by 14
“Hence, adopting the same approach as [17], we tune the parameters of each algorithm manually until we observe the best convergence rate.”
InfluentialConstrained multi-cluster game: Distributed Nash equilibrium seeking over directed graphs
Nguyen, D. T., Bianchi, M., Dörfler, F., Nguyen, D. T., & Nedić, A. (2024) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc56724.2024.10885852 · Cited by 6
Self-citationDecentralized proximal splitting algorithms for composite constrained convex optimization
Zheng, L., Ran, L., Li, H., Feng, L., Wang, Z., Lü, Q., & Xia, D. (2022) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2022.07.053 · Cited by 5
Subgradient-Push Is of the Optimal Convergence Rate
Lin, Y., & Liu, J. (2022) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc51059.2022.9992842 · Cited by 8
“As a future work, the proposed tool is expected to be applicable to analyze other push-sum based algorithms and improve/simplify their convergence analyses, for example, DEXTRA [9] and Push-DIGing [11].”
MethodOnline Coalitional Games for Real-Time Payoff Distribution With Applications to Energy Markets
Raja, A. A., & Grammatico, S. (2023) · IEEE Transactions on Energy Markets Policy and Regulation · doi:10.1109/tempr.2023.3262581 · Cited by 6
Wang, S., Li, Y., Qi, G., et al. (2023) · Drones · doi:10.3390/drones7070473 · Cited by 5
Accelerated Distributed Nesterov Optimization Subject to Complex Constraints and Its Applications
Liu, B., Du, W., & Li, Z. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3331334 · Cited by 5
“Recent work [20], [21], [22] improved these results by introducing the smoothness and μ -strongly convex, and the linear optimization rate can be guaranteed by historical gradient information and gradient estimation strategy, which is highly in accordance with centralized gradient method.”
BackgroundPrivate and Robust Distributed Nonconvex Optimization via Polynomial Approximation
He, Z., He, J., Chen, C., & Guan, X. (2024) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2024.3354875 · Cited by 7
“It is weaker than that requiring connectivity at every time and is sufficient for information flow from one agent in networks to another [13].”
BackgroundMethodInfluentialDiscrete-Time Distributed Optimization for Linear Uncertain Multi-Agent Systems
Liu, T., Bin, M., Notarnicola, I., et al. (2023) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc49753.2023.10384140 · Cited by 5
“Alterna-tively, gradient tracking has been introduced in distributed optimization to track the gradient of the global cost function and achieve faster convergence [5], [6].”
BackgroundProvably Accelerated Decentralized Gradient Methods Over Unbalanced Directed Graphs
Song, Z., Shi, L., Pu, S., & Yan, M. (2024) · SIAM Journal on Optimization · doi:10.1137/22m148570x · Cited by 11
“Approaches such as EX-TRA [48], NIDS [28], and gradient tracking methods [14, 15, 35, 42, 65] achieve linear convergence rates for smooth and strongly convex functions over undirected networks with (symmetric) doubly stochastic mixing matrices.”
BackgroundMethodInfluentialDu, B., Kong, N., & Sun, D. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3381603 · Cited by 5
“To address the challenges, we build on the decentralized sum-tracking technique [27].”
MethodMUSIC: Accelerated Convergence for Distributed Optimization With Inexact and Exact Methods
Wu, M., Liao, H., Ding, Z., & Xiao, Y. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3376421 · Cited by 8
“This discrepancy primarily arises from the fact that ACC-GT and the DIGing methods require three and two communication rounds per iteration, respectively, whereas our exact MUSIC, along with exact diffusion/EXTRA, only requires one.”
InfluentialDistributed Heavy-Ball Over Time-Varying Digraphs With Barzilai-Borwein Step Sizes
Yang, S., Shen, Y. ‐., Cao, J., & Huang, T. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3382232 · Cited by 6
“Lemma 2 (Property of ˜ W [ τ ] k , see [24]): In Lemma 2, δ depends on τ .”
InfluentialAdaptive Consensus: A Network Pruning Approach for Decentralized Optimization
Shah, S. M., Berahas, A. S., & Bollapragada, R. (2024) · SIAM Journal on Optimization · doi:10.1137/23m1599379 · Cited by 8
“• For τ = 1 and where Q is the mixing matrix corresponding to the reference graph, AC-GT reduces to a standard gradient tracking algorithm ( GTA ) [33].”
InfluentialDecentralized Variational Inference Frameworks for Multi-Object Tracking on Sensor Networks
Li, Q., Gan, R., & Godsill, S. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3584248 · Cited by 5
“Secondly, a gradient tracking scheme is applied to improve its convergence speed, which also guarantees convergence when using a constant stepsize [25], [26].”
Asynchronous Distributed Optimization With Delay-free Parameters
Wu, X., Liu, C., Magnússon, S., & Johansson, M. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3590953 · Cited by 11
“With the popular Metropolis averaging matrix [30] where (cid:6) +1 , the advantage of the asynchronous DGD-ATC over Prox-DGD becomes stronger in denser networks.”
Nesterov Accelerated Gradient Tracking With Adam for Distributed Online Optimization
Su, Y., Sheng, Q., Shi, X., et al. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3604059 · Cited by 5
“[29] proposed DIGing and proved that the gradient tracking method can be e ff ectively applied to time-varying networks.”
Distributed Deterministic Asynchronous Algorithms in Time-Varying Graphs Through Dykstra Splitting
Pang, C. H. J. (2019) · SIAM Journal on Optimization · doi:10.1137/18m1168297 · Cited by 5
Decentralized Optimization with Edge Sampling
Zhang, C., Li, Q., & Zhao, P. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/93 · Cited by 5
A Unified Contraction Analysis of a Class of Distributed Algorithms for Composite Optimization
Xu, J., Sun, Y., Tian, Y., & Scutari, G. (2019) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap45676.2019.9022451 · Cited by 7
“When G = 0, several distributed schemes have been proposed in the literature enjoying such a property; examples include EXTRA [1], AugDGM [2], NEXT [3], SONATA [4], [5], DIGing [6], NIDS [7], Exact Diffusion [8], MSDA [9], and the distributed algorithms in [10], [11], and [12].”
BackgroundInfluentialPenalty-Based Method for Decentralized Optimization over Time-Varying Graphs
Rogozin, A., & Gasnikov, A. V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-62867-3_18 · Cited by 6
Distributed Constrained Optimization with Linear Convergence Rate
Dong, Z., Mao, S., Du, W., & Tang, Y. S. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264327 · Cited by 6
“For time-varying topology, an R-linearly convergent algorithm called DIGing (distributed inexact gradient & gradient tracking) algorithm [14] is proposed which shows the success application of gradient tracking technique and the small gain theorem.”
MethodWang, D., Fang, X., Wan, Y., et al. (2020) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc42340.2020.9303916 · Cited by 5
“Some other discrete-time optimization algorithms were also studied in the literature, including the augmented distributed gradient algorithm [8], DIGing [9], and distributed subgradient-free algorithm [10].”
MethodLinear Convergence for Distributed Optimization Without Strong Convexity
Yi, X., Zhang, S., Yang, T., Chai, T., & Johansson, K. H. (2020) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9304381 · Cited by 8
“For example, in [14]–[17], the authors assumed that each local cost function is strongly convex.”
BackgroundSelf-Healing First-Order Distributed Optimization
Ridgley, I. L. D., Freeman, R. A., & Lynch, K. (2021) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc45484.2021.9683487 · Cited by 5
Enhanced Gradient Tracking Algorithms for Distributed Quadratic Optimization via Sparse Gain Design
Carnevale, G., Bin, M., Notarnicola, I., Marconi, L., & Notarstefano, G. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.405 · Cited by 5
A Decentralized Stochastic Algorithm for Coupled Composite Optimization With Linear Convergence
Lü, Q., Liao, X., Deng, S., & Li, H. (2022) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2022.3190743 · Cited by 8
A Modified Gradient Flow for Distributed Convex Optimization on Directed Networks
Jahvani, M., & Guay, M. (2022) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc53348.2022.9867634 · Cited by 5
“The latter assumption has already been investigated, for instance, in [10], [11], [12], [16], [17], [18], [19], [20].”
BackgroundA Small Gain Analysis of Single Timescale Actor Critic
Olshevsky, A., & Gharesifard, B. (2023) · SIAM Journal on Control and Optimization · doi:10.1137/22m1483335 · Cited by 5
Self-citationXie, T., Chen, G., & Liao, X. (2019) · Neural Computing and Applications · doi:10.1007/s00521-019-04116-w · Cited by 6
“By means of the statistical analysis, the event-triggered times of 10 agents are [27, 25, 27, 31, 29, 30, 32, 24, 41, 34], and the average event-triggered times are 30.”
MethodDistributed Optimization Over Time-Varying Networks With Minimal Connectivity
Wu, X., & Lu, J. (2020) · IEEE Control Systems Letters · doi:10.1109/lcsys.2020.2971835 · Cited by 5
CPCA: A Chebyshev Proxy and Consensus based Algorithm for General Distributed Optimization
He, Z., He, J., Chen, C., & Guan, X. (2020) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc45564.2020.9147791 · Cited by 4
On the Linear Convergence of Two Decentralized Algorithms
Li, Y., & Yan, M. (2021) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-021-01833-y · Cited by 9
Primal-dual methods for large-scale and distributed convex optimization and data analyticsPreprint
Jakovetić, D., Bajović, D., Xavier, J., et al. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4427250 · Cited by 5
Distributed Nonconvex Optimization: Gradient-free Iterations and Globally Optimal SolutionPreprint
He, Z., He, J., Chen, C., & Guan, X. (2020) · arXiv (Cornell University) · Cited by 5
Distributed Online Optimization via Gradient Tracking with Adaptive Momentum.Preprint
Carnevale, G., Farina, F., Notarnicola, I., & Notarstefano, G. (2020) · arXiv (Cornell University) · Cited by 5
On the Benefits of Multiple Gossip Steps in Communication-Constrained Decentralized OptimizationPreprint
Hashemi, A., Acharya, A., Das, R., Vikalo, H., Sanghavi, S., & Dhillon, I. S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10643 · Cited by 7
“…of decentralized optimization schemes including those with uncompressed communication that require strong convexity to a achieve linear rate, e.g. [32,42,45,60] – except the recent results in [52,59] with full communication – we only assume the Polyak-Łojasiewicz condition which enables us to…”
BackgroundCompressed Gradient Tracking for Decentralized Optimization with Linear Convergence.Preprint
Li, Z., Liao, Y., Huang, K., & Pu, S. (2021) · arXiv (Cornell University) · Cited by 3
Distributed Optimization with Projection-free DynamicsPreprint
Chen, G., Yi, P., Hong, Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.02450 · Cited by 5
“In fact, the gradient tracking method in [24], [25] motivates our algorithm design.”
MethodImproving the Transient Times for Distributed Stochastic Gradient MethodsPreprint
Huang, K., & Pu, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.04851 · Cited by 5
“Problem (1.1) has been studied extensively in the literature using various distributed algorithms [32, 18, 19, 13, 6, 7, 28, 5, 26, 17, 34, 25], among which the distributed gradient descent (DGD) method proposed in [18] has drawn the greatest attention.”
InfluentialInnovation Compression for Communication-efficient Distributed Optimization with Linear ConvergencePreprint
Zhang, J., You, K., & Xie, L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.06697 · Cited by 5
Berahas, A. S., Bollapragada, R., & Wei, E. (2021) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2021.3094906 · Cited by 17
“exact [1, 36–40]: methods that converge to the optimal solution using a fixed steplength on strongly convex functions; 5.”
MethodLan, X., Yan, J., Zhao, Z., et al. (2025) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2025.3570999 · Cited by 4
“…of i th missile. e ci is the temporal difference error as follows: Then, based on the gradient descent method and the Distributed Inexact Gradient and Gradient Tracking (DIGing) algorithm [35], [36], [37], distributed collaborative learning is performed on the weights of the critic network.”
Duan, M., Zhu, S., Yang, Z., et al. (2025) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2025.3574852 · Cited by 4
“Problem(7)isastandarddistributedoptimiza-tionproblem,andtherearelotsofdistributedalgorithmseither indiscrete-time[6],[7],[8],[9],[10],[11]orincontinuous-time[12],[13]thatcanbeusedtosolveit.”
Han, D., Liu, K., Xia, Y., & Xie, L. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3579218 · Cited by 4
“Note that the assumption on doubly stochastic weighted matrix in [5] can usually be satisfied by employing the Metropolis weight protocol [24] that should be executed collaboratively by the nodes over an undirected network, however, the computation of the Metropolis weight can be easily corrupted by…”
On Graphs with Finite-Time Consensus and Their Use in Gradient Tracking
Nguyen, E. D. H., Jiang, X., Ying, B., & Uribe, C. A. (2025) · SIAM Journal on Optimization · doi:10.1137/24m1661455 · Cited by 14
“Gradient Tracking (GT) (Di Lorenzo and Scutari, 2016; Nedić et al., 2017) is a well-studied decentralized algorithm for solving Problem (1), and various formulations of TV-GT exist in the literature.”
InfluentialAn Analysis Tool for Push-Sum-Based Distributed Optimization
Lin, Y., Zhu, Z., & Liu, J. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3596669 · Cited by 5
“Althoughtheanalysisofthepush-sumalgorithmiselegant,the analysesofpush-sum-basedalgorithmsareoftenquitecomplicated, e.g.,subgradient-push[6],DEXTRA[12](apush-sum-basedvariant ofthewell-knownEXTRAalgorithm[13])andPush-DIGing[14].”
Zhang, K., Yang, Z., Liu, H., Zhang, T., & Başar, T. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.1290 · Cited by 4
“Since we consider a more general setting with a time-varying communication network, several recent work (Zhu and Mart́ınez, 2013; Nedic et al., 2017; Tatarenko and Touri, 2017; Hong and Chang, 2017) may apply.”
ResultA Decentralized Variance-Reduced Method for Stochastic Optimization Over Directed Graphs
Qureshi, M. I., Xin, R., Kar, S., & Khan, U. A. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413600 · Cited by 5
An accelerated algorithm for distributed optimization with Barzilai-Borwein step sizes
Zhang, X., Liu, S., & Zhao, N. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108748 · Cited by 7
An event-triggering algorithm for decentralized stochastic optimization over networks
Li, Y., Chen, Y., Lü, Q., et al. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.07.006 · Cited by 4
Gradient Tracking with Multiple Local SGD for Decentralized Non-Convex Learning
Ge, S., & Chang, T. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10383768 · Cited by 4
“A range of algorithms and techniques have been developed to achieve this goal, including distributed gradient descent (DGD) [8], de-centralized stochastic gradient descent (DSGD) [9], [10], D 2 [11], and the gradient tracking (GT) method [12]–[16].”
MethodNian, X., Li, F., & Liu, D. (2024) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2024.3372889 · Cited by 4
“Up to now, numerous outstanding distributed optimization algorithms have emerged, which can be broadly categorized into two types according to their design ideas: 1) algorithms based on primal-dualdynamics[3],[4],[5],[6]and2)algorithmsbasedon gradienttrackingmethods[7],[8],[9].”
Communication-Efficient Federated Optimization over Semi-Decentralized Networks
Wang, H., & Chi, Y. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10447382 · Cited by 3
He, Z., He, J., Chen, C., & Guan, X. (2024) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2024.3395723 · Cited by 8
“By exploiting current and historical local gradients to track the global gradient, recent works achieve linear convergence rates for strongly convex and smooth objectives [3], [5], [6], [8].”
Distributed aggregative optimization over directed networks with column-stochasticity
Zhou, Q., Zhang, K., Zhou, H., Lü, Q., Liao, X., & Li, H. (2024) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2024.107492 · Cited by 5
Two-Group Distributed Optimization Under Cooperative-Collaborative Networks With Linear Convergence
Dong, Z., Mao, S., Du, W., Jin, Y., & Tang, Y. S. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2024.3524548 · Cited by 4
“Inspired by the Small Gain Theorem [17], this manuscript proposes the following Multi-Loop Small Gain Theorem for more complex relations.”
InfluentialThe Effectiveness of Local Updates for Decentralized Learning Under Data Heterogeneity
Wu, T., Li, Z., & Sun, Y. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3533208 · Cited by 12
“The idea leads to the renowned DGT algorithm with exact convergence [10]–[12].”
BackgroundMethodChen, M., Wang, D., Xu, X., et al. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3535458 · Cited by 4
“Fortunately, distributed optimization on unbalanced digraphs [16], [17], [18] has been investigated, which provides insights for designing NE learning algorithms.”
Unified Analysis of Decentralized Gradient Descent: A Contraction Mapping Framework
Larsson, E. G., & Michelusi, N. (2025) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2025.3557332 · Cited by 17
“Other extensions of DGD are gradient tracking [9]–[11] and DGD for optimization over directed topologies [12].”
A Unifying System Theory Framework for Distributed Optimization and Games
Carnevale, G., Mimmo, N., & Notarstefano, G. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3573800 · Cited by 4
“Perturbed Consensus Dynamics: This scheme [47], [56] has beenextensivelyusedindistributedoptimization[45],[49],[57], [58],[59]andgames[11],[31].”
Han, S. (2019) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2019.8815081 · Cited by 5
“In this paper, we study the distributed gradient tracking algorithm in [13] or equivalently the DIGing algorithm in [11], in which the update equations are given by where and η > 0 is the step size.”
MethodMulti-Agent Natural Actor-Critic Reinforcement Learning Algorithms
Trivedi, P., & Hemachandra, N. (2021) · Dynamic Games and Applications · doi:10.1007/s13235-022-00449-9 · Cited by 12
Extremum Seeking Tracking for Derivative-Free Distributed Optimization
Mimmo, N., Carnevale, G., Testa, A., & Notarstefano, G. (2024) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2024.3510368 · Cited by 5
Decentralized Parallel SGD Based on Weight-Balancing for Intelligent IoV
Yuan, Y., Yu, J., Cheng, X., Zou, Z., Yu, D., & Cai, Z. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3216709 · Cited by 4
“Thus, Nedic et al. [13] designed a novel algorithm using the distributed inexact gradient tracking method, it is suitable for time-varying general undirected / unbalanced directed graphs.”
MethodDISH: A Distributed Hybrid Primal-Dual Optimization Framework to Utilize System Heterogeneity
Niu, X., & Wei, E. (2022) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc51059.2022.9993156 · Cited by 4
A stochastic averaging gradient algorithm with multi‐step communication for distributed optimization
Zheng, Z., Yan, Y., Feng, L., Du, Z., Li, H., Wang, Z., & Hu, J. (2023) · Optimal Control Applications and Methods · doi:10.1002/oca.2973 · Cited by 4
“Versions of gradient tracking methods have developed in References 16-20.”
MethodInfluentialRate analysis of dual averaging for nonconvex distributed optimization
Liu, C., Wu, X., Yi, X., et al. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.117 · Cited by 4
“Different from the deterministic time-varying networks considered in (Nedic et al., 2017; Xin et al., 2021; Jiang et al., 2022), Assumption 2 does not require the communication network to be connected every finite time steps.”
BackgroundDistributed algorithms of solving linear matrix equations via double-layered networks
Huang, Y., Zeng, X., Meng, Z., et al. (2024) · Automatica · doi:10.1016/j.automatica.2024.111662 · Cited by 4
Berahas, A. S., Bollapragada, R., & Gupta, S. (2024) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-024-02554-8 · Cited by 18
“Examples of such methods include, but are not limited to, Scaffnew [23], FedAvg [18], Scaffold [17], Local-SGD [14] and FedLin [24].”
InfluentialLei, J., Yi, P., Chen, J., & Hong, Y. (2020) · European Control Conference (ECC) · doi:10.23919/ecc51009.2020.9143660 · Cited by 3
“Recently, techniques utilizing uncoordinated steplengths have been proposed in [26].”
BackgroundPrivacy-Preserving Distributed Coordination of Distributed Energy Resources
Zholbaryssov, M., Hadjicostis, C. N., & Domínguez-García, A. D. (2020) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9303977 · Cited by 6
“Nevertheless, a number of works attempted to address these challenges by designing robust distributed control strategies (see, e.g., [13], [14]) based on recent advances in the field of distributed control and optimization (see, e.g., [15]–[19]).”
BackgroundMethodInfluentialDistributed Optimization for Mixed-Integer Consensus in Multi-Agent Networks
Liu, Z., & Stursberg, O. (2022) · European Control Conference (ECC) · doi:10.23919/ecc55457.2022.9838543 · Cited by 4
A distributed electricity energy trading strategy under energy shortage environment
Xu, Q., Yu, C., Yuan, X., et al. (2022) · Complex Engineering Systems · doi:10.20517/ces.2022.20 · Cited by 4
“Remark 1 The proposed algorithm is designed based on the combination of the Digging algorithm proposed in [14] and the distributed algorithm presented in [15].”
BackgroundMethodInfluentialAchieving Globally Superlinear Convergence for Distributed Optimization with Adaptive Newton Method
Zhang, J., You, K., & Başar, T. (2020) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc42340.2020.9304321 · Cited by 4
“We compare DAN and DAN-LA with a second-order method ESOM-3 [9] and a first-order method DIGing [2].”
BackgroundMethodInfluentialScalable Average Consensus with Compressed Communications
Toghani, M. T., & Uribe, C. A. (2022) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc53348.2022.9867351 · Cited by 4
“This technique has been extended to optimization and social learning problems [1], [27].”
MethodA Distributed Stochastic Gradient Tracking MethodPreprint
Pu, S., & Nedić, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.07741 · Cited by 4
“A distributed gradient tracking method was proposed in [17]–[19], where the agent-based auxiliary variables yi were introduced to track the average gradients of fi assuming accurate gradient information is available.”
BackgroundMethodSelf-citationGeometric Convergence for Distributed Optimization with Barzilai-Borwein Step SizesPreprint
Gao, J., Liu, X., Dai, Y., Huang, Y., & Yang, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.07852 · Cited by 4
Yi, X., Zhang, S., Yang, T., Johansson, K. H., & Chai, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.03282 · Cited by 3
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.