Showing stat.MEShow all
2 papers · 1 filter
stat.ME2026
A Bayesian approach to learning mixtures of nonparametric components
Yilei Zhang, Yun Wei, Aritra Guha +1
Mixture models are widely used in modeling heterogeneous data populations. A standard approach of mixture modeling assumes that the mixture component takes a parametric kernel form…
stat.ME2025
Distributional Evaluation of Generative Models via Relative Density Ratio
Yuliang Xu, Yun Wei, Li Ma
We propose a function-valued evaluation metric for generative models based on the relative density ratio (RDR) designed to characterize distributional differences between real and…