期刊
JOURNAL OF MACHINE LEARNING RESEARCH
卷 23, 期 -, 页码 -出版社
MICROTOME PUBL
关键词
Information Criterion; Kronecker Product; Low Rank Approximation; Matrix Decomposition; Random Matrix
资金
- National Science Foundation [DMS-1454817, DMS-2027855, DMS-2052949]
- NEC Labs America
This study addresses the problem of matrix approximation and denoising caused by the Kronecker product decomposition. A method called Kronecker product approximation (KoPA) is proposed, which approximates a given matrix by the sum of several Kronecker products of matrices. By using extended information criteria to select the appropriate configuration, the proposed method is able to select the true configuration with high probability and outperforms the low rank approximations.
We consider the problem of matrix approximation and denoising induced by the Kronecker product decomposition. Specifically, we propose to approximate a given matrix by the sum of a few Kronecker products of matrices, which we refer to as the Kronecker product ap-proximation (KoPA). Because the Kronecker product is an extensions of the outer product from vectors to matrices, KoPA extends the low rank matrix approximation, and includes it as a special case. Comparing with the latter, KoPA also offers a greater flexibility, since it allows the user to choose the configuration, which are the dimensions of the two smaller matrices forming the Kronecker product. On the other hand, the configuration to be used is usually unknown, and needs to be determined from the data in order to achieve the op-timal balance between accuracy and parsimony. We propose to use extended information criteria to select the configuration. Under the paradigm of high dimensional analysis, we show that the proposed procedure is able to select the true configuration with probability tending to one, under suitable conditions on the signal-to-noise ratio. We demonstrate the superiority of KoPA over the low rank approximations through numerical studies, and several benchmark image examples.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据