arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1001.0492math.STstat.TH
收藏

核随机矩阵的谱

The spectrum of kernel random matrices

Noureddine El Karoui

摘要:

我们将自己置于高维统计推断的设置中,其中感兴趣的数据集中的变量$p$的数量与观测值$n$的数量具有相同的数量级。我们考虑某些核随机矩阵的谱,特别是$n\times n$矩阵,其$(i,j)$的第一个条目是$f(X_i'X_j/p)$或$f(\Vert X_i-X_j\Vert^2/p)$,其中$p$是数据的维数,并且$X_i$是独立的数据向量。这里假定$f$是局部光滑函数。这项研究的动机是统计和计算机科学中出现的问题,这些矩阵被用来执行,除其他外,非线性版本的主成分分析。令人惊讶的是,我们发现,在高维中,对于我们分析的模型,问题基本上是线性的-这与有时用来证明这些方法的使用的逻辑学是不一致的。分析还突出了在随机矩阵理论中广泛研究的模型的某些特性,并提出了一些问题,它们的相关性作为工具,在实践中遇到的高维数据建模。

英文摘要:

We place ourselves in the setting of high-dimensional statistical inference where the number of variables $p$ in a dataset of interest is of the same order of magnitude as the number of observations $n$. We consider the spectrum of certain kernel random matrices, in particular $n\times n$ matrices whose $(i,j)$th entry is $f(X_i'X_j/p)$ or $f(\Vert X_i-X_j\Vert^2/p)$ where $p$ is the dimension of the data, and $X_i$ are independent data vectors. Here $f$ is assumed to be a locally smooth function. The study is motivated by questions arising in statistics and computer science where these matrices are used to perform, among other things, nonlinear versions of principal component analysis. Surprisingly, we show that in high-dimensions, and for the models we analyze, the problem becomes essentially linear--which is at odds with heuristics sometimes used to justify the usage of these methods. The analysis also highlights certain peculiarities of models widely studied in random matrix theory and raises some questions about their relevance as tools to model high-dimensional data encountered in practice.

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。

↑