Department of Statistics Unitmark
Dietrich College of Humanities and Social Sciences

Important Feature PCA for high dimensional clustering

Publication Date

July, 2014

Publication Type

Tech Report


Jiashun Jin, Wanjie Wang


We consider a clustering problem where we observe feature vectors $X_i \in R^p$, $i = 1, 2, \ldots, n$, from $K$ possible classes. The class labels are unknown and the main interest is to estimate them. We are primarily interested in the modern regime of $p \gg n$, where classical clustering methods face challenges.

We propose Influential Features PCA (IF-PCA) as a new clustering procedure. In IF-PCA, we select a small fraction of features with the largest Kolmogorov-Smirnov (KS) scores, where the threshold is chosen by adapting the recent notion of Higher Criticism, obtain the first $(K-1)$ left singular vectors of the post-selection normalized data matrix, and then estimate the labels by applying the classical k-means to these singular vectors. It can be seen that IF-PCA is a tuning free clustering method.
We apply IF-PCA to $10$ gene microarray data sets. The method has competitive performance in clustering. Especially, in three of the data sets, the error rates of IF-PCA are only $29\%$ or less of the error rates by other methods. We have also rediscovered a phenomenon on empirical null by Efron on microarray data.

With delicate analysis, especially post-selection eigen-analysis, we derive tight probability bounds on the Kolmogorov-Smirnov statistics and show that IF-PCA yields clustering consistency in a broad context. The clustering problem is connected to the problems of sparse PCA and low-rank matrix recovery, but it is different in important ways. We reveal an interesting phase transition phenomenon associated with these problems and identify the range of interest for each.