arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.21391stat.ME

贝叶斯Wasserstein排斥高斯混合模型

Bayesian Wasserstein Repulsive Gaussian Mixture Models

Weipeng Huang, Tin Lok James Ng

AI总结:

本文提出贝叶斯Wasserstein排斥高斯混合模型,基于Wasserstein距离促进聚类分离,并在非参数密度估计框架内建立后验收缩率,验证了其有效性。

摘要:

我们开发了贝叶斯Wasserstein排斥高斯混合模型,以促进良好分离的聚类。与现有专注于分离分量均值的排斥混合方法不同,我们的方法基于Wasserstein距离鼓励混合分量之间的分离。我们在非参数密度估计框架内建立了后验收缩率。使用阻塞-折叠Gibbs采样器进行后验采样。通过模拟研究和实际数据应用,我们证明了所提模型的有效性。

英文摘要:

We develop the Bayesian Wasserstein repulsive Gaussian mixture model that promotes well-separated clusters. Unlike existing repulsive mixture approaches that focus on separating the component means, our method encourages separation between mixture components based on the Wasserstein distance. We establish posterior contraction rates within the framework of nonparametric density estimation. Posterior sampling is performed using a blocked-collapsed Gibbs sampler. Through simulation studies and real data applications, we demonstrate the effectiveness of the proposed model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑