Augmented distributed gradient methods for multi-agent optimization under uncoordinated constant stepsizes
By Jinming Xu, Shanying Zhu, Y. C. Soh, Lihua Xie. IEEE Conference on Decision and Control, 2015
376 citations recorded by the source corpus.
Subfields: Computer Networks and Communications, Public Health, Environmental and Occupational Health
View Paper: https://www.semanticscholar.org/paper/e7127ac404c981dff58d18c2527872eb0ed5ca7c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Networks and Communications
In Public Health, Environmental and Occupational Health
Citations in the corpus
- Distributed nonconvex constrained optimization over time-varying digraphs (2018, methodology): “We can now show that the algorithms recently studied in [30,33,50,52] are all special cases of SONATA and NEXT, earlier proposed in [12–14].”
- A geometrically convergent method for distributed optimization over time-varying graphs (2016, methodology): “References [25] and [26] both utilize dynamic average consensus and thereby propose two primal-only-like algorithms working over directed graph, Aug-DGM and NEXT, respectively.”
- Accelerated Distributed Nesterov Gradient Descent (2017, methodology): “We will compare our algorithm (Acc-DNGDSC or Acc-DNGD-NSC) with Distributed Gradient Descent (DGD) in [22] with a vanishing step size, the “EXTRA” algorithm in [31] (with W̃ = W+I 2 ), the algorithm studied in [36, 7, 33, 28, 23, 35, 21] (we name it “Acc-DGD”), the “D-NG” method in [13].”
- Walkman: A Communication-Efficient Random-Walk Algorithm for Decentralized Optimization (2018, methodology): “This approach includes well-known algorithms such as diffusion [1], [2] and consensus [7], [8], distributed ADMM (D-ADMM) [9]–[13], EXTRA [14], PG-EXTRA [15], gradient tracking [16]–[21], exact diffusion [22], NIDS [23] and beyond.”
- A Decentralized Proximal-Gradient Method With Network Independent Step-Sizes and Separated Convergence Rates (2017, background): “To be specific, works [38], [42] relax the step-size rule to allow uncoordinated step-sizes across agents.”
- Optimization over time-varying directed graphs with row and column-stochastic matrices (2018, methodology): “In this paper, we use gradient estimation as was used in [24]–[26], [28] and extend the AB algorithm introduced in [33] to time-varying, random directed graphs.”
- Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs (2016, methodology): “The algorithm we will study in this paper crucially relies on tracking differences of gradients and is a minor variation of algorithms that have appeared in [73,74] and [15–17].”
- Push–Pull Gradient Methods for Distributed Optimization in Networks (2018, methodology): “The structure of Algorithm 1 resembles that of the gradient tracking methods as in [9], [25] with the doubly stochastic matrix being split into a row-stochastic matrix and a column-stochastic matrix.”
- A survey of distributed optimization (2019, methodology): “…based on the combination of the d istributed i nexact g radient method and the gradient track ing technique (abbreviated as DIGing), developed independently in Nedi ´c et al. (2017a) ; Qu and Li (2018) ; Xu, Zhu, Soh, and Xie (2015, 2018a) and Nedi ´c, Olshevsky, Shi, and Uribe (2017b) .”
- Exact Diffusion for Distributed Optimization and Learning—Part I: Algorithm Development (2017, methodology): “It should be emphasized that condition (2), which is repeated in (3), is different from all previous algorithms studied in [23], [32]–[34], [36], [38], [42], [43], which require A to be symmetric and doubly stochastic (i.”
- Harnessing smoothness to accelerate distributed optimization (2016, neutral): “Reference [24] focuses on uncoordinated step sizes.”