TY - GEN
T1 - Incremental ADMM with Privacy-Preservation for Decentralized Consensus Optimization
AU - Ye, Yu
AU - Chen, Hao
AU - Xiao, Ming
AU - Skoglund, Mikael
AU - Poor, H. Vincent
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/6
Y1 - 2020/6
N2 - The alternating direction method of multipliers (ADMM) has recently been recognized as a promising approach for large-scale machine learning models. However, very few results study ADMM from the aspect of communication costs, especially jointly with privacy preservation. We investigate the communication efficiency and privacy of ADMM in solving the consensus optimization problem over decentralized networks. We first propose incremental ADMM (I-ADMM), the updating order of which follows a Hamiltonian cycle. To protect privacy for agents against external eavesdroppers, we investigate I-ADMM with privacy preservation, where randomized initialization and step size perturbation are adopted. Using numerical results from simulations, we demonstrate that the proposed I-ADMM with step size perturbation can be both communication efficient and privacy preserving.
AB - The alternating direction method of multipliers (ADMM) has recently been recognized as a promising approach for large-scale machine learning models. However, very few results study ADMM from the aspect of communication costs, especially jointly with privacy preservation. We investigate the communication efficiency and privacy of ADMM in solving the consensus optimization problem over decentralized networks. We first propose incremental ADMM (I-ADMM), the updating order of which follows a Hamiltonian cycle. To protect privacy for agents against external eavesdroppers, we investigate I-ADMM with privacy preservation, where randomized initialization and step size perturbation are adopted. Using numerical results from simulations, we demonstrate that the proposed I-ADMM with step size perturbation can be both communication efficient and privacy preserving.
KW - Decentralized optimization
KW - alternating direction method of multipliers (ADMM)
KW - privacy preserving
UR - http://www.scopus.com/inward/record.url?scp=85090423098&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090423098&partnerID=8YFLogxK
U2 - 10.1109/ISIT44484.2020.9174276
DO - 10.1109/ISIT44484.2020.9174276
M3 - Conference contribution
AN - SCOPUS:85090423098
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 209
EP - 214
BT - 2020 IEEE International Symposium on Information Theory, ISIT 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Symposium on Information Theory, ISIT 2020
Y2 - 21 July 2020 through 26 July 2020
ER -