Accelerated Hierarchical Density Clustering
read the original abstract
We present an accelerated algorithm for hierarchical density based clustering. Our new algorithm improves upon HDBSCAN*, which itself provided a significant qualitative improvement over the popular DBSCAN algorithm. The accelerated HDBSCAN* algorithm provides comparable performance to DBSCAN, while supporting variable density clusters, and eliminating the need for the difficult to tune distance scale parameter. This makes accelerated HDBSCAN* the default choice for density based clustering. Library available at: https://github.com/scikit-learn-contrib/hdbscan
This paper has not been read by Pith yet.
Forward citations
Cited by 3 Pith papers
-
Photometric Identification of Unresolved Binary Stars in Nearby Open Star Clusters
Empirical isochrones in photometric diagrams enable identification of unresolved binaries in eight nearby open clusters, yielding binary fractions of 0.16-0.44 and mass ratio modes around 0.4-0.8.
-
Unsupervised Chemo-Dynamical Dissection of the Inner Galactic Halo: Discovery of Five Accreted Substructures with SDSS-V and Gaia
A blind 12D chemo-dynamical clustering analysis with UMAP and HDBSCAN on SDSS-V DR19 and Gaia DR3 data recovers seven known halo substructures and reports five new tightly bound candidates FO1-FO5.
-
Astrophysical Parameters of 5056 Open Star Clusters from Bayesian Nested Sampling with PARSEC Isochrones
A homogeneous catalogue of age, [Fe/H], heliocentric distance and E(G_BP-G_RP) for 5056 open clusters is produced from uniform Bayesian nested sampling of Gaia DR3 CMDs against PARSEC isochrones with physically motiva...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.