Search Machine Learning Repository: Fast Stochastic Alternating Direction Method of Multipliers
Authors: Wenliang Zhong and James Kwok
Conference: Proceedings of the 31st International Conference on Machine Learning (ICML-14)
Year: 2014
Pages: 46-54
Abstract: We propose a new stochastic alternating direction method of multipliers (ADMM) algorithm, which incrementally approximates the full gradient in the linearized ADMM formulation. Besides having a low per-iteration complexity as existing stochastic ADMM algorithms, it improves the convergence rate on convex problems from $\mO(1/\sqrt{T})$ to $\mO(1/T)$, where $T$ is the number of iterations. This matches the convergence rate of the batch ADMM algorithm, but without the need to visit all the samples in each iteration. Experiments on the graph-guided fused lasso demonstrate that the new algorithm is significantly faster than state-of-the-art stochastic and batch ADMM algorithms.
[pdf] [BibTeX]

authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).