EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
Open accessThe DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index; 7 of the 19 sources its claims cite were checked for support.
Abstract
Recently, there has been growing interest in solving consensus optimization problems in a multiagent network. In this paper, we develop a decentralized algorithm for the consensus optimization problem $\mathrm{minimize}_{x\in\mathbb{R}^p}~\bar{f}(x)=\frac{1}{n}\sum_{i=1}^n f_i(x),$ which is defined over a connected network of $n$ agents, where each function $f_i$ is held privately by agent $i$ and encodes the agent's data and objective. All the agents shall collaboratively find the minimizer while each agent can only communicate with its neighbors. Such a computation scheme avoids a data fusion center or long-distance communication and offers better load balance to the network. This paper proposes a novel decentralized exact first-order algorithm (abbreviated as EXTRA) to solve the consensus optimization problem. “Exact” means that it can converge to the exact solution. EXTRA uses a fixed, large step size, which can be determined independently of the network size or topology. The local variable of every agent $i$ converges uniformly and consensually to an exact minimizer of $\bar{f}$. In contrast, the well-known decentralized gradient descent (DGD) method must use diminishing step sizes in order to converge to an exact minimizer. EXTRA and DGD have the same choice of mixing matrices and similar per-iteration complexity. EXTRA, however, uses the gradients of the last two iterates, unlike DGD which uses just that of the last iterate. EXTRA has the best known convergence rates among the existing synchronized first-order decentralized algorithms for minimizing convex Lipschitz--differentiable functions. Specifically, if the $f_i$'s are convex and have Lipschitz continuous gradients, EXTRA has an ergodic convergence rate $O(\frac{1}{k})$ in terms of the first-order optimality residual. In addition, as long as $\bar{f}$ is (restricted) strongly convex (not all individual $f_i$'s need to be so), EXTRA converges to an optimal solution at a linear rate $O(C^{-k})$ for some constant $C>1$.
Overview
CoChat Summary
TL;DR
EXTRA is a synchronous decentralized exact first-order algorithm for consensus optimization that can use a fixed step size independent of network size and converges to an exact solution. It achieves an ergodic O(1/k) rate for convex Lipschitz-differentiable objectives and a linear rate under restricted strong convexity.
Key findings
- EXTRA uses a fixed large step size and converges exactly, unlike DGD with a fixed step size, which stalls in an O(α)-neighborhood and requires diminishing step sizes for exact convergence.
- Under Assumptions 1–3 and step size \(0<\alpha<2\lambda_{\min}(\tilde W)/L_f\), the sequence \(z_k\) converges to an optimal \(z^*\), with contraction factor \(\zeta=1-\alpha L_f/(2\lambda_{\min}(\tilde W))\); running-average progress is \(O(1/k)\), running-best progress is \(o(1/k)\), and running-average optimality residuals are \(O(1/k)\).
- If \(g(x)=f(x)+\frac{1}{4\alpha}\|x\|^2_{\tilde W-W}\) is restricted strongly convex with constant \(\mu_g>0\), then with proper step size \(\alpha<2\mu_g\lambda_{\min}(\tilde W)/L_f^2\), \(\|z_k-z^*\|_G^2\) converges Q-linearly at \(O((1+\delta)^{-k})\), and \(\|x_k-x^*\|_{\tilde W}^2\) converges R-linearly at the same rate.
- Numerical experiments: in decentralized least squares with \(n=10\), \(m_i=1\), \(p=5\), connectivity ratio \(r=0.5\), \(L_f=1\), and \(\|x^*-x_0\|=300\), DGD with fixed step size and EXTRA show similar linear convergence for the first 200 iterations, after which DGD slows and stalls while EXTRA continues. In decentralized logistic regression with \(n=200\), \(r=0.2\), \(m_i=10\), \(p=20\), and 2000 samples, EXTRA outperforms DGD and shows linear exact convergence.
Methods
- Design: a synchronous decentralized first-order algorithm where each agent holds a local copy \(x^{(i)}\) and communicates only with neighbors; EXTRA is derived by taking the difference of two DGD updates and uses gradients of the last two iterates.
- Data/sample: numerical tests on decentralized least squares, decentralized robust least squares with Huber loss, and decentralized logistic regression over randomly generated connected networks.
- Analysis: convergence is established under mixing-matrix assumptions, convex Lipschitz-differentiable objectives, and solution existence; rates are derived via a contraction recursion, ergodic averaging, and restricted strong convexity.
Limitations
- The paper states EXTRA is “far from perfect” and that more work is needed to adapt it to asynchronous and dynamic network settings; these are left as open questions.
- The paper notes it is open whether \(\|z_k-z_{k+1}\|_G^2\) is monotonic; if monotonicity could be shown, the rates would hold for the last point in the running sequence. It also states that proving linear convergence under the numerically observed larger step size \(O(1/L_f)\) remains open.
- The paper states that determining \(\mu_g\) or a lower bound is tricky except when each \(f_i\) is restricted strongly convex, and that deriving an optimal step size and explicit linear rate is “quite tricky and messy.” The numerical results are described as preliminary.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures

![Fig. 4.2 Plot of residuals ‖ x k -x ∗ ‖ F ‖ x 0 -x ∗ ‖ F . Constant α = 0 . 5276 is the theoretical critical step size given for DGD in [36]. For DGD with diminishing step sizes O (1 /k 1 / 3 ) and O (1 /k 1 / 2 ) , we have hand-optimized their initial step sizes as 10 α and 20 α , respectively. The initial large step sizes have helped them (the red and purple curves) realize faster convergence initially.](https://figures.cochat.ai/paper-figures/4f2c85fb730e4c6eaeaa955cda38aeac/extra-an-exact-first-order-algorithm-for-decentralized-consensus-optimization-figure-2.png)
![Fig. 4.3 Plot of residuals ‖ x k -x ∗ ‖ F ‖ x 0 -x ∗ ‖ F . Constant α = 0 . 0059 is the theoretical critical step size given for DGD in [36]. For DGD with diminishing step sizes O (1 /k 1 / 3 ) and O (1 /k 1 / 2 ) , we have hand-optimized their initial step sizes as 10 α and 20 α , respectively.](https://figures.cochat.ai/paper-figures/d5f55fab59f84fe6834d6cb2909bb298/extra-an-exact-first-order-algorithm-for-decentralized-consensus-optimization-figure-3.png)
Verification
Claims the paper makes
6 Valid · 1 Not valid · 9 Not checked · 58 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“On the other hand, properly reducing α k enables exact convergence , namely, that each x k ( i ) converges to the same exact solution.”
What the sources say
- Misattributedcites [36] [36] K. Yuan, Q. Ling, and W. Yin , On the Convergence of Decentralized Gradient Descent , arXiv preprint arXiv:1310.7063, (2013). 1.1, 2.1, 2.4, 4.1, 4.1, 4.2, 4.3 - sourceExperimental — accuracy not yet measured
Our copy disclaims the diminishing-stepsize result for itself: §1.3 (Contribution and notation) states 'Since our analysis uses a fixed stepsize, the local solutions will not be asymptotically consensual. To adapt our analysis to diminishing stepsizes, significant changes will be needed,' and every rate in Theorems 2-3 and Remarks 1-3 lands in an O(alpha/(1-beta))-neighborhood rather than the exact solution. The only place the paper states the claim's point is §1.2 (Related methods): 'Convergence to x* can be achieved by using diminishing stepsizes in [8,11,29] at the price of slower rates of convergence' — i.e., it credits exact convergence under diminishing stepsizes to other works it cites, without reporting or relying on it. Reference [8] in our copy is Duchi, Agarwal and Wainwright, 'Dual averaging for distributed optimization: convergence analysis and network scaling,' IEEE TAC 57 (2012) (with [11] Jakovetic, Xavier, Moura and [29] also credited). (LLM, conf=0.82) It matches “Dual averaging for distributed optimization: convergence analysis and network scaling” (2012) instead.
Checked by a reasoning model — may be wrong.
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.
- Misattributed
Every source the paper cites for this claim was checked and supports it.
In the paper
“In contrast, the well-known decentralized gradient descent (DGD) method must use diminishing step sizes in order to converge to an exact minimizer.”
- Also stated in: § EXTRA: AN EXACT FIRST-ORDER ALGORITHM FOR DECENTRALIZED CONSENSUS OPTIMIZATION ∗ · p. 4 · plain
“properly reducing α k enables exact convergence , namely, that each x k ( i ) converges to the same exact solution.”
What the sources say
- Supportedcites [36] [36] K. Yuan, Q. Ling, and W. Yin , On the Convergence of Decentralized Gradient Descent , arXiv preprint arXiv:1310.7063, (2013). 1.1, 2.1, 2.4, 4.1, 4.1, 4.2, 4.3 - source
Section 1.2 (Related methods) states that with a fixed stepsize the listed algorithms 'and iteration (4) in particular' converge to a neighborhood of x* rather than x* itself, and that convergence to x* can be achieved by using diminishing stepsizes (at the price of slower rates) — exactly the necessity the claim attributes. Section 1.3 reinforces this: 'Since our analysis uses a fixed stepsize, the local solutions will not be asymptotically consensual,' and the Abstract/Theorems 2-3 give only O(α/(1-β))-neighborhood landing levels for fixed α. The only mild caveat is that the diminishing-stepsize exact-convergence results are credited to references [8,11,29] rather than proved here for iteration (4), but the paper's own statement of the fixed-stepsize limitation for DGD covers the claim. (LLM, conf=0.85)
boostedstates 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.
- Also stated in: § EXTRA: AN EXACT FIRST-ORDER ALGORITHM FOR DECENTRALIZED CONSENSUS OPTIMIZATION ∗ · p. 4 · plain
Every source the paper cites for this claim was checked and supports it.
In the paper
“(iii) min t ≤ k { a t } = o ( 1 k ) .”
What the sources say
- Supportedcites [6] [6] D. Davis and W. Yin , Convergence Rates of Splitting Algorithms for Optimization . arXiv preprint arXiv:1406.4834, 2014. 1 - source
Section 2 ('Summable sequence convergence lemma', Lemma 3, p. 8) states Part 4 'No monotonicity', defining the best-so-far sequence and asserting that '(a_j^best) is monotonically nonincreasing and the above bounds continue to hold when a_k is replaced with a_k^best', while the Part 1a proof on the same page gives a_k = o(1/(Λ_k − Λ_⌈k/2⌉)) = o(1/(k+1)) when (λ_j) is bounded away from 0 (i.e. unweighted summability). Together these yield exactly the claim: a nonnegative sequence with finite sum has running minimum o(1/k) (the source writes o(1/(k+1)), the same rate up to index shift). The remark on p. 9 confirms the setting — Part 1 generalizes the known result that a nonnegative, summable, monotonic sequence converges at o(1/(k+1)) — and p. 12 applies Lemma 3 to a running minimum, min_{i=0,…,k}{‖e_i‖}. (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
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“An EXTRA update is, therefore, a DGD update with a cumulative correction term.”
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.
A conclusion the paper draws from its own results — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In this subsection we prove that EXTRA with a proper step size reaches linear convergence if the original objective ¯ f is restricted strongly convex.”
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.
31 more claims
Create a free account to see all 74 claims and to verify the 7 references still open.
- Probably not a substantial claim. 21
- It may state two separate claims as one. 26
- The quote only partly states this claim. 1
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“EXTRA converges at an o (1 /k ) rate when the objective function in (1) is convex, and it has a Q-linear rate when the objective function is strongly convex.”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [62]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing 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) .”
From Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2017) · cites this paper as [62]
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 1: EXTRA · p. 9
“null { U } = (span { 1 } ) ⊥”
§ Algorithm 1: EXTRA · p. 7
“null { W -˜ W } = span { 1 } , null { I -˜ W } ⊇ span { 1 } .”
Citations
Cites
Distributed Subgradient Methods for Multi-Agent Optimization
Nedic, A., & Ozdaglar, A. (2009) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2008.2009515 · Cited by 3,719 · cited 1×
“1) include the (sub)gradient method [21, 25, 36], the (sub)gradient-push method [23, 24], the fast (sub)gradient method [5, 14], and the dual averaging method [8].”
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
Distributed Optimization Over Time-Varying Directed Graphs
Nedic, A., & Olshevsky, A. (2015) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2364096 · Cited by 1,187
Distributed 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
Optimal decentralized protocol for electric vehicle charging
Gan, L., Topcu, U., & Low, S. H. (2013) · IEEE Transactions on Power Systems · doi:10.1109/tpwrs.2012.2210288 · Cited by 997
Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
Duchi, J. C., Agarwal, A., & Wainwright, M. J. (2012) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2011.2161027 · Cited by 947
On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
Shi, W., Ling, Q., Yuan, K., Wu, G., & Yin, W. (2014) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2014.2304432 · Cited by 820
Self-citationDistributed Stochastic Subgradient Projection Algorithms for Convex Optimization
Sundhar Ram, S., Nedić, A., & Veeravalli, V. V. (2010) · Journal of Optimization Theory and Applications · doi:10.1007/s10957-010-9737-7 · Cited by 814 · cited 1×
“1) has additional constraints that force x into a bounded set, which also leads to bounded (sub)gradients and a Hessian, projected first-order algorithms are applicable [27, 37].”
BackgroundOn Distributed Convex Optimization Under Inequality and Equality Constraints
Zhu, M., & Martinez, S. (2012) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2011.2167817 · Cited by 759
Fastest Mixing Markov Chain on a Graph
Boyd, S., Diaconis, P., & Xiao, L. (2004) · SIAM Review · doi:10.1137/s0036144503423264 · Cited by 744
Research works printed but not linked: 3
- [5] I. Chen , Fast Distributed First-Order Methods , master's thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 2012. 1.1, 2.1, 2.4, 4.1 -
- [15] B. Johansson , On Distributed Optimization in Networked Systems , PhD thesis, KTH, 2008. 1 -
- [31] J. Tsitsiklis , Problems in Decentralized Decision Making and Computation , PhD thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, 1984. 2.4 -
Cited by
Items 1,001–1,100 of 1,315
Linear Convergence of distributed estimation with constraints and communication delays
Zhou, Y., & Chen, G. (2023) · Journal of the Franklin Institute · doi:10.1016/j.jfranklin.2023.12.030 · Cited by 1
Topology-Preserving Second-Order Consensus: A Strategic Compensation Approach
Wang, Z., Li, Y., Duan, X., et al. (2023) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc49753.2023.10383971 · Cited by 1
Decentralized Stochastic Optimization With Pairwise Constraints and Variance Reduction
Han, F., Cao, X., & Gong, Y. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3374082 · Cited by 1
Linear convergence of decentralized estimation for statistical estimation using gradient method
Xu, W., Wang, K., & Lian, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127584 · Cited by 1
Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes
Lee, D., Lim, H.-D., & Kim, D. W. (2024) · doi:10.1109/icca62789.2024.10591854 · Cited by 1
Fast Incremental ADMM for Decentralized Consensus Multi-Agent Optimization
You, Y., Ye, Y., Xiao, G., & Xu, Q. (2024) · International Conference on Control and Automation · doi:10.1109/icca62789.2024.10591813 · Cited by 1
Ran, L., Li, H., Zheng, L., & Li, J. Q. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3437249 · Cited by 4
DISH: A Distributed Hybrid Optimization Method Leveraging System Heterogeneity
Niu, X., & Wei, E. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3450351 · Cited by 1
“We compare EXTRA [7], ESOM-0 [16], and different variants of DISH in Algorithm 1 for the two setups.”
InfluentialTillmann, M. H. V., & Yukawa, M. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3451992 · Cited by 1
Distributed Optimization Control for the System with Second-Order Dynamic
Wang, Y., Zhang, H., & Li, Z. Z. (2024) · Mathematics · doi:10.3390/math12213347 · Cited by 1
The Fast Inertial ADMM optimization framework for distributed machine learning
Wang, G., Wang, D., Li, C., & Lei, Y. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.107575 · Cited by 4
Linear Convergence of Asynchronous Gradient Push Algorithm for Distributed Optimization
Li, H., Cheng, H., Lü, Q., Wang, Z., & Huang, T. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3516936 · Cited by 3
Distributed Optimization of Heterogeneous Linear Multi-Agent Systems with Unknown Disturbances
Duan, M., Zhu, S., Yang, Z., et al. (2024) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc56724.2024.10886146 · Cited by 1
“Considering agents modeled with first-order dynamics, many distributed controllers are designed to solve the distributed optimization problem, such as the distributed subgradient descent [3], EXTRA [4], DIGing [5], Aug-DGM [6], Asyn-DGM [7], distributed ADMM [8] and so on [9]-[10].”
Distributed Random Reshuffling Methods With Improved Convergence
Huang, K., Zhou, L., & Pu, S. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3552743 · Cited by 3
“Decentralized stochastic gradient methods often use unbiased stochastic gradients that are typically obtained by uniform sampling with replacement [2], [3], [4], [5], [6], [7], [8].”
Bazizi, T., Maghenem, M. A., Frasca, P., Loría, A., & Panteley, E. V. (2025) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc57313.2025.11312883
Decentralized Convex Optimization for Wireless Sensor Networks
Kamath, G. (2016) · Digital Archive @ GSU · doi:10.57709/9442990 · Cited by 1
Decentralized optimization approach for power distribution network and microgrid controls
Liu, H. J. (2017) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · Cited by 1
Wang, D., Yin, J., & Wang, W. (2018) · International Conference on Information Science and Technology · doi:10.1109/icist.2018.8426143 · Cited by 1
On Convergence Analysis of Gradient Based Primal-Dual Method of Multipliers
Zhang, G., OrConnor, M., & Li, L. (2018) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp.2018.8450854 · Cited by 1
Distributed Constrained Consensus of Utilities via a Self Evaluation Approach
Wang, X., Sun, C., & Sun, T. (2019) · IEEE Access · doi:10.1109/access.2019.2939018 · Cited by 1
Distributed Output Optimization for Discrete-time Linear Multi-agent Systems
Tang, Y., Zhu, H., & Lv, X. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8866362 · Cited by 1
Liang, S., Cheng, S., & Peng, K. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8866018 · Cited by 1
Linear Speedup in Saddle-Point Escape for Decentralized Non-Convex Optimization
Vlaski, S., & Sayed, A. H. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9054327 · Cited by 1
A randomized incremental primal-dual method for decentralized consensus optimization
Chen, C., Chen, Y., & Ye, X. (2019) · Analysis and Applications · doi:10.1142/s0219530519410082 · Cited by 2
“This issue is fixed by the decentralized exact first-order algorithm (EXTRA) developed in [38].”
MethodDistributed Stochastic Algorithm for Convex optimization Problem Over Time-varying Directed Graphs
Cheng, S., Wang, Y., & Hong, Y. (2019) · International Conference on Control and Automation · doi:10.1109/icca.2019.8899958 · Cited by 1
Distributed Proximal Point Algorithm for Constrained Optimization over Unbalanced Graphs
Li, X., Feng, G., & Xie, L. (2019) · International Conference on Control and Automation · doi:10.1109/icca.2019.8899938 · Cited by 3
Polynomial Escape-Time from Saddle Points in Distributed Non-Convex Optimization
Vlaski, S., & Sayed, A. H. (2019) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap45676.2019.9022458 · Cited by 1
On the Comparison between Primal and Primal-dual Methods in Decentralized Dynamic Optimization
Xu, W., Yuan, K., Yin, W., & Ling, Q. H. (2019) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf44664.2019.9049028 · Cited by 1
“These methods include EXTRA [18], NIDS [19], exact diffusion [20], and decentralized gradient tracking (DGT) [21]–[25].”
MethodSelf-citationRow-Stochastic Matrices Based Distributed Optimization Algorithm With Uncoordinated Step-Sizes
Li, H., Wang, J., & Wang, Z. (2019) · International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS) · doi:10.1109/iccss48103.2019.9115478 · Cited by 4
“To make up for the deficiencies of the above methods [9], [13], [16], Shi et al. in [17] employed a coordinated step-size and modified the update of the standard gradient algorithm such that the algorithm linearly converged to the global optimization solution.”
MethodResultInfluentialLi, H., Lü, Q., Wang, Z., Liao, X., & Huang, T. (2020) · Springer eBooks · doi:10.1007/978-981-15-6109-2_2 · Cited by 1
Distributed Stochastic Optimization: Variance Reduction and Edge-Based Method
Li, H., Lü, Q., Wang, Z., Liao, X., & Huang, T. (2020) · Springer eBooks · doi:10.1007/978-981-15-6109-2_8 · Cited by 1
Primal-dual algorithm for distributed optimization with local domains on signed networks
Ren, X., Li, D., Xi, Y., Pan, L., & Shao, H. (2020) · Chinese Control Conference (CCC) · doi:10.23919/ccc50068.2020.9189564 · Cited by 1
Distributed Optimization Over Markovian Switching Random Network
Yi, P., & Li, L. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264492
Accelerated Row-stochastic Optimization over Directed Graphs with Uncoordinated Step Sizes
Zhou, K., Du, Z., & Li, H. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264515 · Cited by 1
Sun, Y., & Shahrampour, S. (2021) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc50511.2021.9482802 · Cited by 1
Decentralized Max-Min Resource Allocation for Monotonic Utility Functions
Wu, S., Xi, P., & Tian, G. (2021) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps51825.2021.9484502 · Cited by 5
Toghani, M. T., & Uribe, C. A. (2022) · European Journal of Control · doi:10.1016/j.ejcon.2022.100682 · Cited by 1
Distributed Convex Optimization on the Nonnegative Orthant
Jahvani, M., & Guay, M. (2022) · European Control Conference (ECC) · doi:10.23919/ecc55457.2022.9838106 · Cited by 1
Feng, L., Ran, L., Meng, G., Tang, J., Ding, W., & Li, H. (2022) · Entropy · doi:10.3390/e24091278 · Cited by 1
Aminian, B., Benam, K. D., & Varagnolo, D. (2022) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53654.2022.9945400 · Cited by 1
Distributed Primal-dual Optimization for Heterogeneous Multi-agent Systems
Li, Y., Voulgaris, P. G., & Freris, N. M. (2022) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc51059.2022.9992775 · Cited by 1
Marquis, D. J., Jaoude, D. A., Farhood, M., & Woolsey, C. A. (2023) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc55779.2023.10156353 · Cited by 1
Communication-Efficient Distributed Optimization with Adaptability to System Heterogeneity
Yu, Z., & Freris, N. M. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10383755 · Cited by 2
A Unified View of Decentralized Algorithms for Sparse Linear Regression
Maros, M., & Scutari, G. (2023) · IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing · doi:10.1109/camsap58249.2023.10403504 · Cited by 1
Distributed, scalable and gossip-free consensus optimization with application to data analysisPreprint
Pakazad, S. K., Naesseth, C. A., Lindsten, F., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.02469 · Cited by 1
Communication-Efficient Projection-Free Algorithm for Distributed OptimizationPreprint
Li, Y., Qu, C., & Xu, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07841 · Cited by 1
Data Rates for Network Linear EquationsPreprint
Lei, J., Yi, P., Shi, G., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.03203 · Cited by 1
Dynamic Average Diffusion with randomized Coordinate UpdatesPreprint
Ying, B., Yuan, K., & Sayed, A. H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.08901 · Cited by 1
“There are several interesting properties associated with the dynamic diffusion strategy (16).”
BackgroundFirst-order Methods with Convergence Rates for Multi-agent Systems on Semidefinite Matrix SpacesPreprint
Majlesinasab, N., Yousefian, F., & Feizollahi, M. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.05900 · Cited by 1
Decentralized Approximate Newton Methods for In-Network OptimizationPreprint
Wei, H., Qu, Z., Wu, X., et al. (2019) · arXiv (Cornell University) · Cited by 1
Jiang, X., Zeng, X., Sun, J. Q., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.13067 · Cited by 1
Variance-Reduced Stochastic Learning by Networked Agents under Random ReshufflingPreprint
Yuan, K., Ying, B., Liu, J., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.01384 · Cited by 1
On linear convergence of two decentralized algorithmsPreprint
Li, Y., & Yan, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.07225 · Cited by 1
Systematic Design of Decentralized Algorithms for Consensus OptimizationPreprint
Han, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.01023 · Cited by 1
“This includes, among others, the distributed gradient descent method [10] (which is, in fact, decentralized despite its name), DIGing [9], [14], and EXTRA [15].”
Distributed Optimization Over Markovian Switching Random NetworkPreprint
Yi, P., & Li, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09862 · Cited by 1
A Private and Finite-Time Algorithm for Solving a Distributed System of Linear EquationsPreprint
Gade, S., Liu, J., & Vaidya, N. H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.04680 · Cited by 3
Accelerated Decentralized Dual AveragingPreprint
Liu, C., Shi, Y., & Li, H. (2020) · arXiv (Cornell University) · Cited by 1
Decentralized Learning with Lazy and Approximate Dual GradientsPreprint
Liu, Y., Sun, Y., & Yin, W. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.01748 · Cited by 1
Self-citationZhang, J., Ling, Q. H., & So, A. M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.10157 · Cited by 1
“We compare Newton tracking with the first-order algorithms, including gradient tracking [21], EXTRA [15] and DLM [17].”
MethodSelf-citationSun, Y., & Shahrampour, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.06747
Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge ComputingPreprint
Chen, H., Ye, Y., Xiao, M. B., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.00914 · Cited by 1
Parallel and Distributed algorithms for ML problemsPreprint
Dvinskikh, D., Gasnikov, A. V., Rogozin, A., & Beznosikov, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.09585 · Cited by 1
“Особенно отметим работы [4, 72, 56, 51, 65] с хорошим запасом оригинальных идей.”
Zeroth-Order Feedback Optimization for Cooperative Multi-Agent SystemsPreprint
Tang, Y., Ren, Z., & Li, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09728 · Cited by 1
Decentralized Approximate Newton Methods for Convex Optimization on Networked SystemsPreprint
Wei, H., Qu, Z., Wu, X., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.09481 · Cited by 1
Efficient Consensus Model based on Proximal Gradient Method applied to Convolutional Sparse ProblemsPreprint
Silva, G., & Rodríguez, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.10100 · Cited by 2
Dependable Distributed Nonconvex Optimization via Polynomial ApproximationPreprint
He, Z., He, J., Chen, C., & Guan, X. (2021) · arXiv (Cornell University) · Cited by 2
A Federated Data-Driven Evolutionary AlgorithmPreprint
Xu, J., Jin, Y., Du, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08288 · Cited by 1
Distributed Newton Optimization with Maximized Convergence RatePreprint
Marelli, D., Xu, Y. K., Fu, M., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.08726 · Cited by 1
Decentralized Statistical Inference with Unrolled Graph Neural NetworksPreprint
Wang, H., Shen, Y., Wang, Z., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.01555 · Cited by 1
“PG-EXTRA: PG-EXTRA [5] is a decentralized proximal gradient method, which is an extension of the decentralized exact first-order algorithm (EXTRA) [26].”
On the Convergence of NEAR-DGD for Nonconvex Optimization with Second Order GuaranteesPreprint
Iakovidou, C., & Wei, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.14233 · Cited by 1
Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoTPreprint
Lei, W., Ye, Y., Xiao, M. B., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.00481 · Cited by 1
Optimal Gradient Tracking for Decentralized OptimizationPreprint
Song, Z., Shi, L., Pu, S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.05282 · Cited by 1
“EXTRA [51] is the first gradient-type method that achieves linear convergence for strongly convex and smooth objective functions by introducing an extra correction term to DGD. Subsequently, distributed ADMM methods [5, 29], NIDS [27], and exact diffusion method [68] were also shown to exhibit linear…”
Finite-Time Consensus Learning for Decentralized Optimization with Nonlinear GossipingPreprint
Chen, J., Wang, S., Carin, L., & Tao, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02949 · Cited by 3
Distributed Sparse Regression via PenalizationPreprint
Yao, J., Scutari, G., Sun, Y., & Honnappa, H. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.06530 · Cited by 5
A Distributed Parallel Optimization Algorithm via Alternating Direction Method of MultipliersPreprint
Liu, Z., Guo, F., Wang, W., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.10494 · Cited by 1
Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement LearningPreprint
Zhao, X., Lei, J., Li, L., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.12961 · Cited by 1
“Decentralized double stochastic averaging gradient [42] was the first de-centralized variance reduction method, obtained by combining exact first order algorithm [43] and SAGA [33] , and linear convergence was shown under strong convexity of local functions and Lipschitz continuity of local gradients.”
In-situ Data Analytics In Cyber-Physical Systems
Zhao, L. (2016) · Digital Archive @ GSU · doi:10.57709/8501627
Learning overcomplete representations from distributed data: a brief review
Raja, H., & Bajwa, W. U. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2228897
Lei, J., Chen, H.-F., & Fang, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1607.06623
A fast algorithm for distributed optimization over directed networks
Zeng, J., & He, T. (2016) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2016.7574793 · Cited by 1
Optimization over directed graphs: Linear convergence rate
Xi, C., & Khan, U. A. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7952958
Slavakis, K., Yamada, I., & Ono, S. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953050
Distributed convex optimization with a row-stochastic matrix over directed graphs
Zhang, Y., Lü, Q., Li, H., & Zhang, H. (2017) · International Workshop on Complex Systems and Networks (IWCSN) · doi:10.1109/iwcsn.2017.8276535 · Cited by 1
Pang, C. H. J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.07734
SUBGRADIENT PROJECTION OVER DIRECTED GRAPHS USING SURPLUS CONSENSUS
Xin, R., Xi, C., & Khan, U. A. (2018) · IEEE Data Science Workshop (DSW) · doi:10.1109/dsw.2018.8439884
A Proximal Gradient Algorithm for Composite Consensus Optimization over Directed Graphs
Zeng, J., He, T., Ouyang, S., Wang, M., & Chang, X. (2017) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber.2017.8446454
Distributed Optimization in Discrete-time Multi-Agent Systems with Independent Step Size
Lian, J., & Chen, Y. (2018) · Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE) · doi:10.23919/sice.2018.8492556
Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODEPreprint
Zhang, J., Uribe, C. A., Mokhtari, A., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.02521
Communication-efficient decentralised algorithms for seismic tomography with sensor networks
Zhao, L. (2019) · International Journal of Parallel Emergent and Distributed Systems · doi:10.1080/17445760.2019.1577416
Kajiyama, Y., Hayashi, N., & Takai, S. (2019) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e102.a.343
Gradient-Free Multi-Agent Nonconvex Nonsmooth OptimizationPreprint
Hajinezhad, D., & Zavlanos, M. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.04650
A Fast Proximal Gradient Algorithm for Decentralized Composite Optimization over Directed NetworksPreprint
Zeng, J., He, T., & Wang, M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1609.03784
A Chebyshev-Accelerated Primal-Dual Method for Distributed OptimizationPreprint
Seidman, J. H., Fazlyab, M., Pappas, G. J., & Preciado, V. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1810.06713
Two-step Fixed-point proximity algorithms for multi-block separable convex problemsPreprint
Qia, L., Xu, Y., & Zhang, N. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1601.01852
“To this end, we first review a lemma presented in [31].”
Su, Y., Shi, Y., & Sun, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.10169
Nested Distributed Gradient Methods with Stochastic Computation ErrorsPreprint
Iakovidou, C., & Wei, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.13400
Spectral-like gradient method for distributed optimization
Jakovetić, D., Krejić, N., & Jerinkić, N. K. (2019) · IEEE EUROCON - International Conference on Computer as a Tool (EUROCON) · doi:10.1109/eurocon.2019.8861761
Corrected Gradient Methods for Distributed optimization
Qiu, Z., Xie, L., & You, K. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8866156
Li, R. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865672
Decentralized Consensus Optimization Based on Parallel Random WalkPreprint
Yu, Y., Chen, H., Ma, Z., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.09747
Metadata
- Authors
- Shi, W., Ling, Q., Wu, G., & Yin, W.
- Venue
- SIAM Journal on Optimization
- Published
- 2015-01
- Volume
- 25
- Issue
- 2
- Pages
- 944-966
- ISSN
- 1052-6234 (ISSN-L)
- 1095-7189
- OpenAlex
- W1571416372
- Cited by
- 1,261
- References
- 25
- Citations by year
- 2026: 75 · 2025: 116 · 2024: 131 · 2023: 131 · 2022: 145 · 2021: 138 · 2020: 158 · 2019: 140 · 2018: 97 · 2017: 62 · 2016: 43 · 2015: 21
- FWCI
- 85.01
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- SIAM Journal on Optimization (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (0748839, 1317602)
- National Natural Science Foundation of China (61004137)
- China Scholarship Council
- Ministry of Industry and Information Technology of the People's Republic of China
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed Sensor Networks and Detection Algorithms
- Keywords
- multi-agent systems, large step size, linear convergence, ergodic convergence rate, strongly convex functions, distributed optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
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).
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.