Kernel Principal Component Analysis - Large Datasets

Large Datasets

In practice, a large data set leads to a large K, and storing K may become a problem. One way to deal with this is to perform clustering on your large dataset, and populate the kernel with the means of those clusters. Since even this method may yield a relatively large K, it is common to compute only the top P eigenvalues and eigenvectors of K.

Read more about this topic:  Kernel Principal Component Analysis

Famous quotes containing the word large:

    ... it appears to me that problems, inherent in any writing, loom unduly large when one looks ahead. Though nothing is easy, little is quite impossible.
    Elizabeth Bowen (1899–1973)