A randomized dual consensus ADMM method for multi-agent distributed optimization
作者： Tsung-Hui Chang
DOI: 10.1109/ICASSP.2015.7178630
关键词:
摘要: Recently, the alternating direction method of multipliers (ADMM) has been used for distributed consensus optimization and is shown to converge faster than conventional approaches based on subgradient. In this paper, we consider a convex problem with linearly coupled equality constraint employ dual ADMM (DC-ADMM) solving in fully fashion. particular, by considering non-ideal network where agents can be ON OFF randomly communications among fail probabilistically, propose randomized DC-ADMM that robust against these effects. Moreover, show proposed provably convergent an optimal solution worst-case O(1/k) convergence rate, k iteration number. Simulation results are presented examine practical behavior presence ON/OFF communication links.
sci-hub.se 参考文章(22)
James Kwok, Ruiliang Zhang, Asynchronous Distributed ADMM for Consensus Optimization international conference on machine learning. pp. 1701- 1709 ,(2014)
Bo Yang, Mikael Johansson, Distributed Optimization and Games: A Tutorial Overview Lecture Notes in Control and Information Sciences. ,vol. 406, pp. 109- 148 ,(2010) , 10.1007/978-0-85729-033-5_4
James Franklin, The elements of statistical learning : data mining, inference,and prediction The Mathematical Intelligencer. ,vol. 27, pp. 83- 85 ,(2005) , 10.1007/BF02985802
Angelia Nedić, Asuman E. Ozdaglar, Dimitri P. Bertsekas, Convex Analysis and Optimization ,(2003)
John N. Tsitsiklis, Dimitri P. Bertsekas, Parallel and Distributed Computation: Numerical Methods ,(1989)
Joao FC Mota, Joao MF Xavier, Pedro MQ Aguiar, Markus Püschel, None, D-ADMM: A Communication-Efficient Distributed Algorithm for Separable Optimization IEEE Transactions on Signal Processing. ,vol. 61, pp. 2718- 2723 ,(2013) , 10.1109/TSP.2013.2254478
Tsung-Hui Chang, M. Alizadeh, A. Scaglione, Coordinated home energy management for real-time power balancing power and energy society general meeting. pp. 1- 8 ,(2012) , 10.1109/PESGM.2012.6345639
Ron Bekkerman, Mikhail Bilenko, John Langford, Scaling up machine learning: parallel and distributed approaches knowledge discovery and data mining. pp. 4- ,(2011) , 10.1145/2107736.2107740
Minghui Zhu, S. Martinez, On Distributed Convex Optimization Under Inequality and Equality Constraints IEEE Transactions on Automatic Control. ,vol. 57, pp. 151- 164 ,(2012) , 10.1109/TAC.2011.2167817
Chao Shen, Tsung-Hui Chang, Kun-Yu Wang, Zhengding Qiu, Chong-Yung Chi, Distributed Robust Multicell Coordinated Beamforming With Imperfect CSI: An ADMM Approach IEEE Transactions on Signal Processing. ,vol. 60, pp. 2988- 3003 ,(2012) , 10.1109/TSP.2012.2188719