On the Consistency of Quick Shift
arXiv:1710.10646v213 citations
Originality Incremental advance
AI Analysis
This provides theoretical foundations for a widely used clustering method, which is incremental as it builds on existing algorithms.
The paper tackled the problem of establishing statistical consistency for the Quick Shift algorithm in mode and cluster recovery, proving finite sample guarantees under mild assumptions and applying these results to create a consistent modal regression algorithm.
Quick Shift is a popular mode-seeking and clustering algorithm. We present finite sample statistical consistency guarantees for Quick Shift on mode and cluster recovery under mild distributional assumptions. We then apply our results to construct a consistent modal regression algorithm.