TY - GEN
T1 - Zeroth-Order Diffusion Adaptation over Networks
AU - Chen, Jie
AU - Liu, Sijia
AU - Chen, Pin Yu
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/10
Y1 - 2018/9/10
N2 - Diffusion adaptation is an efficient strategy to perform distributed estimation over networks with streaming data. Existing diffusion-based estimation algorithms require the knowledge of analytical forms of the cost functions or their gradients associated with agents. This setting can be restrictive for practical applications where gradient calculation is difficult or systems operate in a black-box manner. Motivated by the advance of the zeroth-order (gradient-free) optimization, in this work we propose the zeroth-order (ZO) diffusion strategy using randomized gradient estimates. We also examine the stability conditions of the proposed ZO-diffusion strategy. Simulations are performed to examine properties of the algorithm and to compare it with its non-cooperative and stochastic gradient counterparts.
AB - Diffusion adaptation is an efficient strategy to perform distributed estimation over networks with streaming data. Existing diffusion-based estimation algorithms require the knowledge of analytical forms of the cost functions or their gradients associated with agents. This setting can be restrictive for practical applications where gradient calculation is difficult or systems operate in a black-box manner. Motivated by the advance of the zeroth-order (gradient-free) optimization, in this work we propose the zeroth-order (ZO) diffusion strategy using randomized gradient estimates. We also examine the stability conditions of the proposed ZO-diffusion strategy. Simulations are performed to examine properties of the algorithm and to compare it with its non-cooperative and stochastic gradient counterparts.
KW - Diffusion adaptation
KW - Distributed estimation
KW - Online learning
KW - Stochastic optimization
KW - Zeroth-order optimization
UR - http://www.scopus.com/inward/record.url?scp=85054235226&partnerID=8YFLogxK
U2 - 10.1109/ICASSP.2018.8461448
DO - 10.1109/ICASSP.2018.8461448
M3 - 会议稿件
AN - SCOPUS:85054235226
SN - 9781538646588
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 4324
EP - 4328
BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018
Y2 - 15 April 2018 through 20 April 2018
ER -