Sciweavers

Share
ML
2015
ACM

Linearized alternating direction method with parallel splitting and adaptive penalty for separable convex programs in machine le

3 years 6 months ago
Linearized alternating direction method with parallel splitting and adaptive penalty for separable convex programs in machine le
Many problems in statistics and machine learning (e.g., probabilistic graphical model, feature extraction, clustering and classification, etc) can be (re)formulated as linearly constrained separable convex programs. The traditional alternating direction method (ADM) or its linearized version (LADM) is for the two-variable case and cannot be naively generalized to solve the multi-variable case. In this paper, we propose LADM with parallel splitting and adaptive penalty (LADMPSAP) to solve multi-variable separable convex programs efficiently. When all the component objective functions have bounded subgradients, we obtain convergence results that are stronger than those of ADM and LADM, e.g., allowing the penalty parameter to be unbounded and proving the sufficient and necessary conditions for global convergence. We further propose a simple optimality measure and reveal the convergence rate of LADMPSAP in an ergodic sense. For programs with extra convex set constraints, we devise a prac...
Zhouchen Lin, Risheng Liu, Huan Li
Added 14 Apr 2016
Updated 14 Apr 2016
Type Journal
Year 2015
Where ML
Authors Zhouchen Lin, Risheng Liu, Huan Li
Comments (0)
books