Communication Efficient Distributed Estimation Over Directed Random Graphs

Sahu, Anit Kumar; Jakovetić, Dušan; Bajović, Dragana; Kar, Soummya

doi:10.1109/eurocon.2019.8861544

Cited by 3 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithmic framework is presented in this Section. The framework subsumes several existing algorithms [13,14,15,16,17,18], and it also includes a new algorithm that will be analysed in this paper.…”

Section: Algorithmic Frameworkmentioning

confidence: 99%

“…To the best of our knowledge, except for a different estimation setting [18], this algorithm has not been studied before. The following assumptions are needed.…”

Section: Convergence Analysismentioning

confidence: 99%

“…All these methods are defined by different variants of sparsification of communications and/or computations along iterations. The class that is considered here subsumes several existing methods [13,14,15,16,17,18]. We also define a novel method in the same class with unidirectional communication and analyze its convergence.…”

Section: Introductionmentioning

confidence: 99%

“…With respect to existing studies, this paper differs along several lines. First, it considers a different class of methods with respect to existing empirical studies, as the considered methods include various strategies for communication sparsification (see [13,14,15,16,17,18]). Second, it provides a novel insights into comparison among different sparsification strategies, as well as the practical benefits with respect to the corresponding always-communicating benchmark.…”

Section: Introductionmentioning

confidence: 99%

“…Also, a theoretical convergence analysis of the new method with unidirectional communication is carried out in this paper. While [18] also considers directed communications, it studies the specific problem of distributed estimation, which translates into quadratic objective functions and stochastic gradient updates. In contrast, our analysis considers generic strongly convex costs.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Performance evaluation and analysis of distributed multi-agent optimization algorithms with sparsified communication

Fodor

Jakovetić

Krejić

et al. 2020

Preprint

View full text Add to dashboard Cite

There has been significant interest in distributed optimization algorithms, motivated by applications in Big Data analytics, smart grid, vehicle networks, etc. While there have been extensive theory and theoretical advances, a proportionally small body of scientific literature focuses on numerical evaluation of the proposed methods in actual practical, parallel programming environments. This paper considers a general algorithmic framework of first and second order methods with sparsified communications and computations across worker nodes. The considered framework subsumes several existing methods. In addition, a novel method that utilizes unidirectional sparsified communications is introduced and theoretical convergence analysis is also provided. Namely, we prove R-linear convergence in the expected norm. A thorough empirical evaluation of the methods using Message Passing Interface (MPI) on a High Performance Computing (HPC) cluster is carried out and several useful insights and guidelines on the performance of algorithms and inherent communication-computational trade-offs in a realistic setting are derived.

show abstract

Section: Algorithmic Frameworkmentioning

confidence: 99%

“…To the best of our knowledge, except for a different estimation setting [18], this algorithm has not been studied before. The following assumptions are needed.…”

Section: Convergence Analysismentioning

confidence: 99%