arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0903.4530math.NAcs.IRcs.NA
收藏

非负张量的非负近似

Nonnegative approximations of nonnegative tensors

University of California, Berkeley(加州大学伯克利分校);University of Nice(尼斯大学)

Lek-Heng Lim, Pierre Comon

AI总结:

研究非负张量分解为最小数量的非负向量外积之和及其对应的简约朴素贝叶斯概率模型,证明该非负PARAFAC近似问题总是存在最优解,适用于任何范数选择及在温和假设下的Bregman散度。

摘要:

我们研究非负张量分解为最小数量的非负向量外积之和及其对应的简约朴素贝叶斯概率模型。我们证明,相应的近似问题(这是非负PARAFAC的核心)总是存在最优解。该结果适用于任何范数选择,并且在温和假设下,甚至适用于Bregman散度。

英文摘要:

We study the decomposition of a nonnegative tensor into a minimal sum of outer product of nonnegative vectors and the associated parsimonious naive Bayes probabilistic model. We show that the corresponding approximation problem, which is central to nonnegative PARAFAC, will always have optimal solutions. The result holds for any choice of norms and, under a mild assumption, even Bregman divergences.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑