A highly scalable parallel algorithm for isotropic total variation models

J. Wang, Q. Li, S. Yang, W. Fan, P. Wonka, J. Ye
Proceedings of the 31st International Conference on Machine Learning ICML, pp. 235-243, (2014)

A highly scalable parallel algorithm for isotropic total variation models

Keywords

Total variation (TV) models, Parallel algorithm , Isotropic ,State-of-the-art algorithms

Abstract

​Total variation (TV) models are among the most popular and successful tools in signal processing. However, due to the complex nature of the TV term, it is challenging to efficiently compute a solution for large-scale problems. State-of-the-art algorithms that are based on the alternating direction method of multipliers (ADMM) often involve solving large-size linear systems. In this paper, we propose a highly scalable parallel algorithm for TV models that is based on a novel decomposition strategy of the problem domain. As a result, the TV models can be decoupled into a set of small and independent subproblems, which admit closed form solutions. This makes our approach particularly suitable for parallel implementation. Our algorithm is guaranteed to converge to its global minimum. With NN variables and np processes, the time complexity is O(N/(ϵnp))O(N/(ϵnp)) to reach an epsilon-optimal solution. Extensive experiments demonstrate that our approach outperforms existing state-of-the-art algorithms, especially in dealing with

Code

-

Sources

Website PDF

See all publications 2014