New distributional clustering method introduced using Wasserstein kernel

Researchers have introduced the distributional determinantal point process (dDPP), a novel method for clustering probability distributions. This dDPP utilizes a sliced Wasserstein kernel and is demonstrated to be a valid point process. The framework allows for a distribution-valued random partition model with a repulsive generalized Bayesian mixture model, placing a dDPP prior over the mixing measure's atoms. The proposed method has been applied to single-cell gene expression data and human epilepsy data, yielding interpretable and well-separated clusters. AI

RANK_REASON The cluster contains a research paper detailing a new statistical methodology. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv stat.ML →

• Distributional Determinantal Point Process
• human epilepsy data
• single-cell gene expression data
• Wasserstein

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →