TY - GEN
T1 - Adaptive consensus ADMM for distributed optimization
AU - Xu, Zheng
AU - Taylor, Gavin
AU - Li, Hao
AU - Figueiredo, Mário A.T.
AU - Yuan, Xiaoming
AU - Goldstein, Tom
N1 - Publisher Copyright:
© Copyright 2017 by the authors(s).
PY - 2017
Y1 - 2017
N2 - The alternating direction method of multipliers (ADMM) is commonly used for distributed model fitting problems, but its performance and reliability depend strongly on user-defined penalty parameters. We study distributed ADMM methods that boost performance by using different fine-tuned algorithm parameters on each worker node. We present a O(1/k) convergence rate for adaptive ADMM methods with node-specific parameters, and propose adaptive consensus ADMM (ACADMM), which automatically tunes parameters without user oversight.
AB - The alternating direction method of multipliers (ADMM) is commonly used for distributed model fitting problems, but its performance and reliability depend strongly on user-defined penalty parameters. We study distributed ADMM methods that boost performance by using different fine-tuned algorithm parameters on each worker node. We present a O(1/k) convergence rate for adaptive ADMM methods with node-specific parameters, and propose adaptive consensus ADMM (ACADMM), which automatically tunes parameters without user oversight.
UR - http://www.scopus.com/inward/record.url?scp=85048554819&partnerID=8YFLogxK
M3 - Conference proceeding
AN - SCOPUS:85048554819
T3 - 34th International Conference on Machine Learning, ICML 2017
SP - 5864
EP - 5877
BT - 34th International Conference on Machine Learning, ICML 2017
PB - International Machine Learning Society (IMLS)
T2 - 34th International Conference on Machine Learning, ICML 2017
Y2 - 6 August 2017 through 11 August 2017
ER -