About this document

Soft-Balanced K-Means Clustering by jefferyleclerc is a document available to read on EtoBox.

This document discusses algorithms for soft-balanced clustering. It summarizes several existing approaches that use multiplicative or additive biases in the k-means assignment function to favor assignment of points to smaller clusters. It then proposes a new method that modifies the k-means objective function to include a penalty term based on cluster size, with the goal of balancing cluster sizes while minimizing total distance from cluster centroids.

Author

jefferyleclerc

Language

EN