A Proximal Gradient Algorithm for Decentralized Composite Optimization
The DOI matches its Crossref record; 36 of the 36 references it cites were found in a registry or an index.
Abstract
This paper proposes a decentralized algorithm for solving a consensus optimization problem defined in a static networked multi-agent system, where the local objective functions have the smooth+nonsmooth composite form. Examples of such problems include decentralized constrained quadratic programming and compressed sensing problems, as well as many regularization problems arising in inverse problems, signal processing, and machine learning, which have decentralized applications. This paper addresses the need for efficient decentralized algorithms that take advantages of proximal operations for the nonsmooth terms. We propose a proximal gradient exact first-order algorithm (PG-EXTRA) that utilizes the composite structure and has the best known convergence rate. It is a nontrivial extension to the recent algorithm EXTRA. At each iteration, each agent locally computes a gradient of the smooth part of its objective and a proximal map of the nonsmooth part, as well as exchanges information with its neighbors. The algorithm is “exact” in the sense that an exact consensus minimizer can be obtained with a fixed step size, whereas most previous methods must use diminishing step sizes. When the smooth part has Lipschitz gradients, PG-EXTRA has an ergodic convergence rate of O(1/k) in terms of the first-order optimality residual. When the smooth part vanishes, PG-EXTRA reduces to P-EXTRA, an algorithm without the gradients (so no “G” in the name), which has a slightly improved convergence rate at o(1/k) in a standard (non-ergodic) sense. Numerical experiments demonstrate effectiveness of PG-EXTRA and validate our convergence results.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“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 [61]
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 8×
“We have hand-op-timized this parameter and the step sizes for DADMM, DSM, and P-EXTRA.”
MethodInfluentialAn Overview of Recent Progress in the Study of Distributed Multi-Agent Coordination
Cao, Y., Yu, W., Ren, W., & Chen, G. (2013) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2012.2219061 · Cited by 2,399
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
Distributed Control of Robotic Networks: A Mathematical Approach to Motion Coordination Algorithms
Bullo, F., Cortés, J., & Martínez, S. (2009) · Princeton University Press eBooks · doi:10.1515/9781400831470 · Cited by 1,509
PROBLEMS IN DECENTRALIZED DECISION MAKING AND COMPUTATION
Τσιτσικλής, Ι. (2014) · doi:10.12681/eadd/3778 · Cited by 1,278
EXTRA: 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 · cited 4×
“When the possibly-nondifferentiable term , we have in (2a) and (2b) and thus (4) In (3a) and (3b), we have and thus (5) The updates (4) and (5) are known as EXTRA, a recent algo-rithm for decentralized differentiable optimization [23].”
InfluentialSelf-citationOn 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 · cited 1×
“The existing algorithms that solve problem (1) include the primal-dual domain methods such as the decentralized alternating direction method of multipliers (DADMM) [16], [21] and the primal domain methods including the distributed sub-gradient method (DSM) [22].”
MethodSelf-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
Fastest Mixing Markov Chain on a Graph
Boyd, S., Diaconis, P., & Xiao, L. (2004) · SIAM Review · doi:10.1137/s0036144503423264 · Cited by 744 · cited 1×
“Typical choices of can be found in [23], [28].”
BackgroundConsensus in Ad Hoc WSNs With Noisy Links—Part I: Distributed Estimation of Deterministic Signals
Schizas, I. D., Ribeiro, A., & Giannakis, G. B. (2008) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2007.906734 · Cited by 685 · cited 14×
“9 k 0 100 200 300 400 500 R el a ti v e E rr o r 10-10 10-8 10-6 10-4 10-2 100 DSM, step size ,k = 9:5=k1=2 DADMM, penalty coe/cient c = 0:0038 P-EXTRA, step size , = 46 k 0 100 200 300 400 500 S u cc es si ve D i, er en ce 10-10 10-5 100 105 DSM, step size ,k = 9:5=k1=2 DADMM, penalty coe/cient c = 0:0038 P-EXTRA, st…”
BackgroundMethodInfluential
Research works printed but not linked: 3
- davis, 2014, ?Convergence rates of relaxed Peaceman-Rachford and ADMM under regularity assumptions ?
- deng, 2013, ?Parallel multi-block ADMM with convergence ?
- 2011, Foundations of Location Analysis
Cited by
Items 201–300 of 368
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
“…the problem min ˜ x ∈ R n m i =1 f i (˜ x ) + g i (˜ x ) , PG-EXTRA that extends [16] and generates two interlaced sequences of iterates in [23], NIDS with uncoordinated and network-independent step-sizes [24], and distributed primal-dual algorithm [25] unifying certain state-of-the-art…”
InfluentialLogarithmic Communication for Distributed Optimization in Multi-Agent Systems
London, P., Vardi, S., & Wierman, A. (2020) · ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS) · doi:10.1145/3393691.3394197 · Cited by 4
“There has been considerable research that seeks to reduce the communication overhead of these approaches, e.g., [7, 9].”
BackgroundRan, L., Li, H., Hu, J., Lü, Q., Wang, Z., Li, Z., & Chen, G. (2024) · IEEE Transactions on Control of Network Systems · doi:10.1109/tcns.2023.3285865 · Cited by 4
“In this section, we explore the connections between PDPA-Dist and PG-EXTRA [26].”
BackgroundMethodInfluentialA Convergence-Motivated Learning-to-Optimize Framework for Decentralized Optimization
He, Y., Shang, Q., Huang, X., Liu, J., & Yuan, K. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3644008 · Cited by 4
“For non-smooth optimization problems, effective algorithms like PG-EXTRA [36], PG-Exact-Diffusion [45], and PG-Gradient-Tracking [46] utilize the proximal gradient method to solve them.”
Finite-Time-Consensus-Based Methods for Distributed optimization
Qu, Z., Wu, X., & Lu, J. (2019) · Chinese Control Conference (CCC) · doi:10.23919/chicc.2019.8865722 · Cited by 4
“Recently, algorithms with constant step-sizes yet still converging to an exact optimum are proposed by exploiting duality [11, 19, 20, 26], which have convergence rate guarantees owing to the constant step-sizes.”
BackgroundCapri: Consensus Accelerated Proximal Reweighted Iteration for A Class of Nonconvex Minimizations
Sun, T., & Li, D. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.2989393 · Cited by 4
Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex functionsPreprint
Zhang, S., Xiao, N., & Liu, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.11565 · Cited by 4
“Some existing works, such as ProxDGD [30], NEXT [31], and PG-EXTRA [32] develop decentralized proximal gradient type methods for (DOP), under the assumption that f i is composed of a differentiable term g i and a convex regularization term r i for all i ∈ [ d ] .”
Cooperative Integrated Sensing and Communication Networks: Analysis and Distributed DesignPreprint
Wang, B., Li, H., Liu, F., Cheng, Z., & Shen, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.13401 · Cited by 4
Elgabli, A. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3566464 · Cited by 3
“The principles of distributed machine learning (ML) are rooted in distributed optimization, encompassing a variety of algorithms broadly classified into primal methods [37], [38], [39] and primal-dual methods [40], [41], [42].”
Wang, B., Li, H., Liu, F., Cheng, Z., & Shen, S. (2026) · IEEE Transactions on Communications · doi:10.1109/tcomm.2026.3657393 · Cited by 3
“Proof: Please refer to Appendix A. Remark 2: The proposed framework is different from the existing PG based decentralized ADMM [48], [49], [50] from the following two aspects.”
Guo, L., Shi, X., Xu, W., & Cao, J. (2026) · Automatica · doi:10.1016/j.automatica.2026.112965 · Cited by 3
Distributed Sparse Optimization With Minimax Concave Regularization
Komuro, K., Yukawa, M., & Cavalcante, R. L. G. (2021) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp49050.2021.9513764 · Cited by 3
Stability of Primal-Dual Gradient Flow Dynamics for Multi-Block Convex Optimization Problems
Ozaslan, I. K., Patrinos, P., & Jovanović, M. R. (2026) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2026.3742142 · Cited by 3
Distributed Stochastic Learning for Composite Sharing Optimization in Consumer Electronics
Lü, Q., Dai, X., Zhang, W., & Ezilarasan, M. R. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3506915 · Cited by 3
“Related known approaches have been studied in [32], [33], [34], [35], [36].”
Distributed Proximal-Correction Algorithm for the Sum of Maximal Monotone Operators
Gong, K., & Zhang, L. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2024.3524119 · Cited by 3
Qiao, N., Chen, C., & Zhu, Z. (2025) · Statistics and Computing · doi:10.1007/s11222-024-10547-w · Cited by 3
“In the decentralized category, various algorithms based on gradient descent and ADMM have been proposed (Mateos et al. 2010; Shi et al. 2015; Li et al. 2019; Chang et al. 2014).”
Exploiting Agent Symmetries for Performance Analysis of Distributed Optimization Methods
Colla, S., & Hendrickx, J. M. (2026) · Open Journal of Mathematical Optimization · doi:10.5802/ojmo.49 · Cited by 3
Decentralized stochastic sharpness-aware minimization algorithm
Chen, S., Deng, X., Xu, D., Sun, T., & Li, D. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106325 · Cited by 3
Gramian-Based Adaptive Combination Policies for Diffusion Learning Over Networks
Erginbas, Y. E., Vlaski, S., & Sayed, A. H. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414449 · Cited by 3
“The iterates can be constructed using a variety of decentralized strategies, including incremental [2], consensus [3–5], diffusion [6, 7], primal-dual [8, 9], proximal [10], augmented Lagrangian [11], or gradient tracking methods [12].”
BackgroundTowards an O(1/t) convergence rate for distributed dual averaging
Liu, C., Li, H., & Shi, Y. (2020) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2020.12.1127 · Cited by 3
“For the purpose of comparison, the distributed projected gradient method (DPG) in Nedic et al. (2010), the distributed dual averaging (DDA) in Duchi et al. (2011), and the PG-EXTRA in Shi et al. (2015) are simulated.”
MethodDecentralized Dual Operator Splitting for Nonsmooth Composite Optimization
Li, H., Ding, W., Wang, Z., Lü, Q., Li, Y., & Xia, D. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3155287 · Cited by 3
Namsak, S., Petrot, N., & Nimana, N. (2023) · Results in Applied Mathematics · doi:10.1016/j.rinam.2023.100370 · Cited by 3
Improved Convergence Rates of P-EXTRA for Non-smooth Distributed optimization
Wu, X., & Lu, J. (2019) · International Conference on Control and Automation · doi:10.1109/icca.2019.8899909 · Cited by 3
“Two exceptions are the distributed proximal gradient algorithm (DPGA) [17] and the proximal exact first-order algorithm (P-EXTRA) [18].”
BackgroundMethodInfluentialOnline Federated Learning over decentralized networks
Zhang, C. (2018) · doi:10.32657/10220/47928 · Cited by 3
On the Performance and Linear Convergence of Decentralized Primal-Dual Methods
Alghunaim, S. A. (2020) · eScholarship (California Digital Library) · Cited by 3
Nash Equilibrium Seeking Over Networks
Salehisadaghiani, F. (2017) · TSpace (University of Toronto) · Cited by 3
A Communication Efficient Quasi-Newton Method for Large-scale Distributed Multi-agent OptimizationPreprint
Li, Y., Voulgaris, P. G., & Freris, N. M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.03759 · Cited by 3
“EXPERIMENTS We evaluate the proposed L-BFGS−ADMM against existing distributed algorithms for multi-agent convex composite optimization problems, namely P2D2 [7] and PG-EXTRA [6].”
MethodStochastic optimization for large-scale machine learning : variance reduction and acceleration
Kulunchakov, A. (2020) · theses.fr (ABES) · doi:10.70675/b976f064zd886z4f8cz90e8z019383735308 · Cited by 3
Majority vote for distributed differentially private sign selection
Liu, W., Tu, J., Mao, X., & Chen, X. (2024) · The Annals of Statistics · doi:10.1214/24-aos2411 · Cited by 2
Online Smooth Graph Learning From Incomplete Data
Chen, Z., Zhang, X., Zhou, M., Xu, Y., Li, C., & Wang, B. (2025) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2025.3589719 · Cited by 2
“The learner-adversary framework naturally aligns with proximal gradient descent (PGD) [51].”
An accelerated primal dual algorithm with backtracking for decentralized constrained optimization
Xu, Q., Aybat, N. S., & Gürbüzbalaban, M. (2026) · Journal of Nonlinear and Variational Analysis · doi:10.23952/jnva.10.2026.3.04 · Cited by 2
“In particular, distributed (sub)gradient schemes, gradient tracking methods, and their accelerated and proximal variants have been extensively studied under a variety of assumptions on smoothness, convexity, and network connectivity, e.g., [18, 22, 32, 38, 49, 50, 54].”
Distributed Optimization of Clique-Wise Coupled Problems
Watanabe, Y., & Sakurama, K. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10383234 · Cited by 2
“Now, to verify the effectiveness of the proposed clique-based algorithms, we conduct simulations for the CL-ADMM with and PG-EXTRA [2], given as follows: [9], and hence an optimal solution can be obtained by the CL-ADMM and CL-FLiP-ADMM with The algorithmic parameters are given as follows.”
Fast and Robust Low-Rank Learning over Networks: A Decentralized Matrix Quantile Regression Approach
Qiao, N., & Chen, C. (2024) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2024.2353640 · Cited by 2
“In addition, Shi et al. (2015) and Li, Shi, and Yan (2019) suggested decentralized proximal gradient descent algorithms to avoid the introduction of the Lagrangian dual.”
Tian, F., Chen, X., Huang, C., & Zhang, Z. (2024) · IEEE Transactions on Communications · doi:10.1109/tcomm.2024.3399265 · Cited by 2
“Fortunately, proximal gradient method can efficiently address the non-smooth convex problems [30], [31], [32].”
Optimal design of resolvent splitting algorithms
Bassett, R., & Barkley, P. (2026) · Mathematical Programming Computation · doi:10.1007/s12532-026-00304-7 · Cited by 2
“All of these works note the potential for decentralized optimization using these methods, and the work in [34] demonstrates their ability to outperform other decentralized methods like P-EXTRA [33].”
Shen, J., Hu, J., & Kammara, E. K. H. (2021) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2021.3087110 · Cited by 2
“, PG-EXTRA, are exploited to solve the row partitioned LASSO [14], [26].”
MethodDistributed regularized online optimization using forward–backward splitting
Yuan, D., Zhang, B., Xu, S., & Zhao, H. (2023) · Control Theory and Technology · doi:10.1007/s11768-023-00134-1 · Cited by 2
Edge-based distributed primal–dual algorithms for seeking generalized Nash equilibria
Li, H., Fan, L., Ran, L., Wang, Z., Zheng, Z., Li, Z., Li, S., Zheng, L., & Li, J. Q. (2024) · European Journal of Control · doi:10.1016/j.ejcon.2024.100990 · Cited by 2
An Edge-based Stochastic Proximal Gradient Algorithm for Decentralized Composite Optimization
Zhang, L., Yan, Y., Wang, Z., & Li, H. (2021) · International Journal of Control Automation and Systems · doi:10.1007/s12555-020-0483-9 · Cited by 2
PRIAG: Proximal Reweighted Incremental Aggregated Gradient Algorithm for Distributed Optimizations
Deng, X., Sun, T., Liu, F., & Huang, F. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60245-1_34 · Cited by 2
Wei, Y., Fang, H., Dou, L., & Yang, Q. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264474 · Cited by 2
“The second category of methods includes proximal-splitting algorithms [11]-[13], which employed the proximal operator [14] to insure the smoothness of algorithms.”
MethodA Distributed Proximal Primal-Dual Algorithm for Nonsmooth Optimization with Coupling Constraints
Wu, X., Wang, H., & Lu, J. (2020) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9303937 · Cited by 2
Performance Optimization of Distributed Primal-Dual Algorithms over Wireless Networks
Yang, Z., Chen, M., Wong, K., Saad, W., Poor, H. V., & Cui, S. R. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500853 · Cited by 2
Yun-shan, L., Xiong, H., Zhou, H. Y., & Guan, X. (2022) · Mathematics · doi:10.3390/math10030357 · Cited by 2
Distributed Optimization Algorithm for Composite Optimization Problems with Non-Smooth Function
Shi, Y., Ran, L., Tang, J., & Wu, X. (2022) · Mathematics · doi:10.3390/math10173135 · Cited by 2
“In undirected networks, Shi et al. design a proximal gradient exact first-order algorithm (PG-EXTRA) for composite optimization problems based on the classical first-order distributed optimization algorithm (EXTRA) [8] in [15].”
MethodYang, Y. Z., Ma, D., & Zhang, Y. (2023) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc55779.2023.10156231 · Cited by 2
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
Wang, J., & Hu, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10652 · Cited by 2
“In addition, f i is differentiable and The assumptions in Assumption 2 are often discussed in composite optimization problems [4, 22, 32–36].”
BackgroundOptimal Decentralized Composite Optimization for Convex FunctionsPreprint
Ye, H., & Chang, X. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.15845 · Cited by 2
“After the work of Alghunaim et al. (2019), a unified framework is proposed to analyze a large group of primal-dual and gradient tracking based algorithms, and show that these algorithms can also achieve linear convergence rates with nonsmooth regularization term such as EXTRA ( PG-EXTRA ) (Shi et al., 2015a), and NIDS…”
InfluentialOn Principled Local Optimization Methods for Federated LearningPreprint
Yuan, H. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.13216 · Cited by 2
Historical Information Accelerates Decentralized Optimization: A Proximal Bundle MethodPreprint
Zhao, Z., Tian, Y., & Wu, X. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.15189 · Cited by 2
“We compare DPBM with Prox-DGD [6], [13] and PG-EXTRA [26], [42] in the synchronous and asynchronous, and 1 x i ( t ) , where x i ( t ) is the value of x i at the t th iteration and f ⋆ is the optimal value of (5).”
Distributed Cooperative and Competitive Optimisation Over Networks
Li, Z. (2021) · Research Explorer (The University of Manchester) · Cited by 2
Adaptive Decentralized Composite Optimization via Three-Operator SplittingPreprint
Chen, X., Kuruzov, I. A., & Scutari, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.17545 · Cited by 2
“As nonadaptive benchmarks, we consider SONATA [35] and PG-EXTRA [34], both relying on constant stepsizes that depend on (global) problem and network parameters.”
Accelerated methods for distributed optimization
Hendrikx, H. (2021) · theses.fr (ABES) · doi:10.70675/285acaadze92cz460az885azb3887e474582 · Cited by 2
Accelerated Distributed Composite Nesterov Gradient Descent Algorithm
Yue, X., & Ni, Y. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9901596 · Cited by 1
Decentralized Sum-of-Nonconvex Optimization
Liu, Z., & Low, B. K. H. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i13.29318 · Cited by 1
A Flexible Framework for Decentralized Composite Optimization with Compressed Communication
Chang, Z., Zhang, Z., Yang, S., & Cao, J. (2024) · Fractal and Fractional · doi:10.3390/fractalfract8120721 · Cited by 1
Enhancing Convergence of Decentralized Gradient Tracking under the KL Property
Chen, X., Scutari, G., & Cao, T. (2026) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2026.3713850 · Cited by 1
A Zeroth-Order Proximal Algorithm for Consensus Optimization
Wang, C., Ou, Z., & Lu, J. (2024) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc56724.2024.10886308 · Cited by 1
Li, C., & Ma, Y. (2025) · Symmetry · doi:10.3390/sym17071159 · Cited by 1
Survey and prospects of distributed optimization in multi-agent systems
Jiang, X., Xianlin, Z. E. N. G., Sun, J. Q., & Chen, J. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0337 · Cited by 1
“这两种经典方法都需要使用衰减步长 , 衰减步长会趋于零 , 13] 以及 EXTRA 的推广方法 为了进一步改善算法的收敛性 , 在切换网络拓扑下 该技术使得本地函数的梯度逐渐逼近全局函数的梯度 该类算法可以使用固定更新步长 .”
Distributed Dual Operator Splitting Algorithm for Nonsmooth Composite Optimization
Li, H., Lü, Q., Xia, D., Wang, X., Wang, Z., Zheng, L., Li, J. Q., & Ran, L. (2025) · Computational intelligence methods and applications · doi:10.1007/978-981-95-0911-9_5 · Cited by 1
An ODE-Based Dynamic Mean-Variance Portfolio Optimisation with Time-Varying Risk Aversion
Alkhudaydi, M. H. (2025) · Computational Economics · doi:10.1007/s10614-025-11152-3 · Cited by 1
Diffusion Learning with Partial Agent Participation and Local Updates
Rizk, E., Chen, S., Yuan, K., & Sayed, A. H. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3739118 · Cited by 1
A novel distributed gradient algorithm for composite constrained optimization over directed network
Ou, M., Zhang, H., Yan, Z., Yang, Z., & Ran, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-36058-4 · Cited by 1
“Subsequently, Shi et al. 25 expanded the EXTRA algorithm by integrating proximal operator mechanisms to effectively manage non-smooth components within the distributed framework, thereby formulating the Proximal Gradient EXact firsT-ordeR Algorithm (PG-EXTRA) algorithm, which effectively handles…”
Privacy Preserving Decentralized Learning With Positive-Incentive Noise
Wang, L., Yang, S., Wan, Y., Xu, W., & Zhang, M.-L. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3672569 · Cited by 1
“Compared to methods LED [55] and EXTRA [56], a primal correction is presented in (7c) to decouple the primal and dual stepsizes, which imposes little additional computation and communication burden, discussed at length in [49].”
Topology-Optimal Multiple Gossip Steps for Decentralized Federated Learning via Gossip Tensor
Zhong, Y., Ma, L., & Yan, X. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3670013 · Cited by 1
“[12] and [34] designed proximal gradient algorithms for decentralized computing.”
Anti-Disturbance Proximal Neural Networks for Composite Resource Allocation
Luan, L., Qi, S., & Qin, S. (2026) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2026.3675092 · Cited by 1
“For example, a consensus-based neural network and an ADMM algorithm were proposed in [4] and [9], respectively, for unconstrained composite distributed optimization problems.”
Byzantine-Resilient Decentralized Optimization for Joint Feature Selection in Multi-Task Networks
Wang, D., Liu, W. T., & Mao, X. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3688176 · Cited by 1
“…these insights, proximal-gradient-based methods have been developed for decentralized composite optimization with separable nonsmooth regularizers [18], while jointly sparse learning over networks has been explored via reweighted (cid:2) q minimization to encourage shared supports across agents…”
Decentralized Optimization With Multiple Local Updates and Network-Independent Stepsizes
Liu, J., & Wang, Y. (2026) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2026.3742745 · Cited by 1
“In addition, we make the following standard assumption [31], [33], [36] regarding the undirected communication network G = {V , E} : Assumption 3: The undirected network G = {V , E} is connected.”
An Inexact Fenchel Dual Gradient Algorithm for Distributed Optimization
Wang, H., & Lu, J. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264365 · Cited by 1
“The proximal gradient exact first-order algorithm (PG-EXTRA) [8], the projected first-order algorithms [9], [10], and the primal-dual algorithms [17]–[22] are able to effectively address convex problems with constraints.”
BackgroundMethodA 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
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
A Penalty Alternating Direction Method of Multipliers for Decentralized Composite Optimization
Zhang, J., So, A. M., & Ling, Q. H. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053138 · Cited by 1
Self-citationLogarithmic Communication for Distributed Optimization in Multi-Agent Systems
London, P., Vardi, S., & Wierman, A. (2020) · ACM SIGMETRICS Performance Evaluation Review · doi:10.1145/3410048.3410105 · Cited by 1
“There has been considerable research that seeks to reduce the communication overhead of these approaches, e.g., [7, 9].”
BackgroundWang, Y., & Liu, S. (2022) · International Conference on Control and Automation · doi:10.1109/icca54724.2022.9831961 · Cited by 1
Feng, L., Ran, L., Meng, G., Tang, J., Ding, W., & Li, H. (2022) · Entropy · doi:10.3390/e24091278 · Cited by 1
Komuro, K., Yukawa, M., & Cavalcante, R. L. G. (2022) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco55093.2022.9909571 · Cited by 1
“By using property − By the triangle inequality and the (firm) nonexpansivity of prox γh , the following inequality holds: Here, An application of PG-EXTRA [7] to the proposed formulation (P 2 ) yields Algorithm 1.”
BackgroundMethodInfluentialWang, H. (2023) · Numerical Algorithms · doi:10.1007/s11075-023-01650-6 · Cited by 1
“EXTRA[28,29]isthenproposed asanexactfirst-orderalgorithmwithlinearconvergencerate.”
Distributed Stable Outlier-Robust Signal Recovery using Minimax Concave Loss
Tillmann, M. H. V., & Yukawa, M. (2023) · Machine learning for signal processing ... · doi:10.1109/mlsp55844.2023.10285947 · Cited by 1
“In the previous work [12], the sparse signal recovery prob-979-8-3503-2411-2 lem has been studied in a distributed setting under the use of the MC penalty to promote sparsity of estimates, where the proximal gradient EXTRA (PG-EXTRA) algorithm [13] was used.”
MethodA Distributed Algorithm for Optimal Energy Management With Network-Independent Stepsize
Guo, L., Shi, X., Zhou, Y., & Cao, J. (2023) · International Conference on Information Science and Technology · doi:10.1109/icist59754.2023.10367147 · Cited by 1
“For distributed composite optimization, several distributed algorithms have been provided, such as IC-ADMM [9], PG-ADMM [10], PG-EXTRA [11], DPPD [6], and PAD [12].”
MethodA distributed algorithm for solving quadratic optimization problems
Jahvani, M., & Guay, M. (2024) · Computers & Chemical Engineering · doi:10.1016/j.compchemeng.2024.108778 · Cited by 1
Tillmann, M. H. V., & Yukawa, M. (2024) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2024.3451992 · Cited by 1
“…i) the problem formulation to characterize the target signal as a minimizer of cost functions, and ii) the algorithm to solve the formulated problem in a distributed fashion [16], [17], [18], [19], [20], [21], [22] (see also [23] for an extensive survey of distributed optimization algorithms).”
MethodDiscrete-time algorithms to supervised learning
Li, Z., & Ding, Z. (2024) · Elsevier eBooks · doi:10.1016/b978-0-44-321636-7.00020-9 · Cited by 1
Nonconvex Multitask Learning Over Networks
Vlaski, S., & Nassif, R. (2024) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63174.2024.10715115 · Cited by 1
Distributed Optimization of Cliquewise Coupled Problems via Three-Operator Splitting
Watanabe, Y., & Sakurama, K. (2025) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2025.3631500 · Cited by 1
“This framework extends beyond conventional pairwise coupled problems (e.g., consensus optimization) and is applicable to broader examples.”
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
Accelerated Decentralized Dual AveragingPreprint
Liu, C., Shi, Y., & Li, H. (2020) · arXiv (Cornell University) · Cited by 1
Gradient-Consensus Method for Distributed Optimization in Directed NetworksPreprint
Khatana, V., Saraswat, G., Patel, S., & Salapaka, M. V. (2019) · arXiv (Cornell University) · Cited by 1
Wang, J., & Hu, G. (2021) · arXiv (Cornell University) · Cited by 1
Data Privacy in Multi-Agent Optimization Under Uncertainty
Margellos, K., Falsone, A., Garatti, S., & Prandini, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-14081-5.00170-7 · Cited by 1
Non-Ergodic Convergence Algorithms for Distributed Consensus and Coupling-Constrained OptimizationPreprint
Qiu, C., & Lin, Z. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.19714 · Cited by 1
“Representative approaches include consensus-based subgradient methods [5] [6], distributed gradient methods [7] [8], primal–dual method [9], and algorithms for composite optimization [10]–[12].”
Tam, M. K., Timms, L., & Zhang, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.12502 · Cited by 1
“One such algorithm is PG-EXTRA [31, 35], applicable when B 1 , . . . , B N are cocoercive with constants 1 /L 1 , . . . , 1 /L N respectively.”
Distributed proximal algorithms for large-scale structured optimization
Latafat, P. (2020) · doi:10.13118/latafat-puya_phd2020 · Cited by 1
van Elst, A., Fercoq, O., Colin, I., & Clémençon, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.20571 · Cited by 1
“Rate variants such as P-EXTRA have been proposed in [13] for synchronous decentralized settings, but they do not naturally extend to asynchronous settings due to the non-linearity of the proximal operator.”
D-ripALM: A Tuning-friendly Decentralized Relative-Type Inexact Proximal Augmented Lagrangian MethodPreprint
Zhu, J., Wang, H., Liang, L., & Yang, L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.06398 · Cited by 1
“• In Section 5.2, we compare D-ripALM with state-of-the-art decentralized algorithms, PG-EXTRA [32] and NIDS [14], on nonsmooth distributed optimization problems to demonstrate its competitiveness relative to representative single-loop methods.”
InfluentialDegeneracy-Aware Resilient Resource Allocation in Cell-Free Cache-Aided MU-MIMO NetworksPreprint
Ghosh, S., Dey, I., & Marchetti, N. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.24611 · Cited by 1
“Rep-resentative examples include decentralized optimization based on alternating direction method of multipliers (ADMM) [14], reinforcement-learning-based resource allocation [15], graph-neural-network-assisted wireless control [16], and Byzantine-resilient distributed optimization and learning…”
Coordinate Update Algorithms: Theory and Applications
Wu, T. (2017) · eScholarship (California Digital Library)
Slavakis, K., Yamada, I., & Ono, S. (2017) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2017.7953050
“Motivated by recent studies on decentralized optimization [18, 19], where a composite convex minimization task is solved by a large number of computer nodes s.”
BackgroundMethods for Decentralized Signal Processing With Big Data
Wai, H.-T., Scaglione, A., & Moulines, É. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-813677-5.00015-8
Metadata
- Authors
- Shi, W., Ling, Q., Wu, G., & Yin, W.
- Affiliations
- University of Science and Technology of China (CN)
- University of California, Los Angeles (US)
- Venue
- IEEE Transactions on Signal Processing
- Published
- 2015-11
- Volume
- 63
- Issue
- 22
- Pages
- 6013-6023
- ISSN
- 1053-587X (ISSN-L)
- 1941-0476
- OpenAlex
- W1627780903
- Cited by
- 307
- References
- 36
- Citations by year
- 2026: 17 · 2025: 30 · 2024: 31 · 2023: 28 · 2022: 36 · 2021: 35 · 2020: 41 · 2019: 27 · 2018: 28 · 2017: 19 · 2016: 15
- FWCI
- 23.64
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Signal Processing (publishedVersion)
- Funders
- National Natural Science Foundation of China (61004137, 61573331)
- National Science Foundation (DMS-1317602)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Distributed Control Multi-Agent Systems
- Physical Sciences › Computer Science › Signal Processing › Sparse and Compressive Sensing Techniques
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Optimization and Variational Analysis
- Keywords
- distributed optimization, consensus optimization, multi-agent systems, proximal gradient method, composite objective function, nonsmooth optimization, fixed step size, ergodic convergence rate, compressed sensing, regularization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.