.png){kind=icon}
返回
Sparse dictionary learning by block proximal gradient with global convergence
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2019.08.028.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The present paper focuses on dictionary learning in the double sparsity model for sparse representation (or approximation). Due to the highly non-convexity and discontinuity of l(0) pseudo-norm, the proofs of convergence for sparse K singular value decomposition (Sparse-KSVD) and online sparse dictionary learning (OSDL) are challenging. To theoretically analyze the convergence, we relax the l(0) pseudo-norm to the convex entry-wise l(1) norm, and reformulate the constrained optimization problem as an unconstrained one leveraging the double-l(1)-regularizer. Therefore, the problem becomes bi-convex. To train a sparse dictionary, an algorithm based on the block proximal gradient (BPG) framework with global convergence is derived. Several experiments are presented to show that our algorithm outperforms Sparse-KSVD and OSDL in some cases. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Sparse dictionary learning
Double sparsity
Sparse representation
Sparse approximation
Block proximal gradient
Convergence
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Small Silencing RNAs in Plants Are Mobile and Direct Epigenetic Modification in Recipient Cells.png)
Science
ScienceIF0
PREAI
分享收藏
查看更多内容