Risk Bounds For Mode Clustering
This work provides theoretical risk bounds for mode clustering, addressing a fundamental problem in nonparametric clustering for researchers and practitioners in statistics and machine learning.
The paper tackles the problem of quantifying the risk of density mode clustering, showing that the clustering risk is very small over high-density regions (cluster cores) and, under low noise conditions, remains small even beyond these cores in high dimensions.
Density mode clustering is a nonparametric clustering method. The clusters are the basins of attraction of the modes of a density estimator. We study the risk of mode-based clustering. We show that the clustering risk over the cluster cores --- the regions where the density is high --- is very small even in high dimensions. And under a low noise condition, the overall cluster risk is small even beyond the cores, in high dimensions.