45
1

A more efficient algorithm to compute the Rand Index for change-point problems

Abstract

In this paper we provide a more efficient algorithm to compute the Rand Index when the data cluster comes from change-point detection problems. Given NN data points and two clusters of size rr and ss, the algorithm runs on O(r+s)O(r+s) time complexity and O(1)O(1) memory complexity. The traditional algorithm, in contrast, runs on O(rs+N)O(rs+N) time complexity and O(rs)O(rs) memory complexity.

View on arXiv
Comments on this paper