.png){kind=icon}
.png){kind=icon}
Return
An incremental decomposition method for unconstrained optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.amc.2014.02.088.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this work we consider the problem of minimizing a sum of continuously differentiable functions. The vector of variables is partitioned into two blocks, and we assume that the objective function is convex with respect to a block-component. Problems with this structure arise, for instance, in machine learning. In order to advantageously exploit the structure of the objective function and to take into account that the number of terms of the objective function may be huge, we propose a decomposition algorithm combined with a gradient incremental strategy. Global convergence of the proposed algorithm is proved. The results of computational experiments performed on large-scale real problems show the effectiveness of the proposed approach with respect to existing algorithms. (C) 2014 Elsevier Inc. All rights reserved.
Keywords:
Large-scale unconstrained optimization
Decomposition
Gradient incremental methods
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.4
Papers:
2.3W
Citations:
3.3W