Moving Up the Cluster Tree with the Gradient Flow
Ery Arias-Castro, Wanli Qiao

TL;DR
This paper demonstrates a theoretical connection between cluster trees and gradient flow, showing how to ascend the cluster hierarchy by following gradient ascent paths, bridging two classical clustering methods.
Contribution
It establishes a formal link between cluster trees and gradient flow, enabling movement up the cluster hierarchy via gradient ascent, which was previously unconnected.
Findings
Shows the correspondence between cluster trees and gradient flow.
Provides a method to move up the cluster hierarchy using gradient ascent.
Bridges two classical clustering approaches from the 1970s.
Abstract
The paper establishes a strong correspondence between two important clustering approaches that emerged in the 1970's: clustering by level sets or cluster tree as proposed by Hartigan and clustering by gradient lines or gradient flow as proposed by Fukunaga and Hostetler. We do so by showing that we can move up the cluster tree by following the gradient ascent flow.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Retrieval and Classification Techniques · Rough Sets and Fuzzy Logic · Face and Expression Recognition
