方法对比

	贝叶斯 K-均值聚类	贝叶斯混合模型
领域	统计学	统计学
方法族	Latent structure	Latent structure
起源年份	2006–2012	1997 (Richardson & Green Bayesian formulation)
提出者	Kulis & Jordan (ICML 2012) formalized the Bayesian nonparametric derivation; Bishop (2006) established the variational Bayesian EM framework for Gaussian mixture models as a probabilistic foundation	Richardson & Green (seminal Bayesian treatment, 1997); broader Bayesian mixture roots trace to Dempster, Laird & Rubin (EM, 1977) and Titterington, Smith & Makov (1985)
类型	Probabilistic clustering / Bayesian nonparametric	Latent-class / model-based clustering
开创性文献	Kulis, B. & Jordan, M. I. (2012). Revisiting k-means: New algorithms via Bayesian nonparametrics. In Proceedings of the 29th International Conference on Machine Learning (ICML), Edinburgh, Scotland, pp. 513–520.	Fruhwirth-Schnatter, S., Celeux, G. & Robert, C. P. (Eds.) (2019). Handbook of Mixture Analysis. CRC Press / Chapman & Hall. ISBN: 9780367733995
别名	Bayesian K-means, probabilistic K-means, Dirichlet K-means, BKM	Bayesian mixture model, BMM, Bayesian model-based clustering, Bayesian finite mixture
相关	6	4
摘要	Bayesian K-means clustering extends the classical K-means algorithm by placing prior distributions over cluster centroids and mixing proportions. This probabilistic framework provides uncertainty estimates for cluster assignments, allows principled model selection for the number of clusters, and regularises centroid estimation — especially valuable when data are scarce or high-dimensional.	Bayesian mixture modeling represents the population as a weighted sum of K component distributions and estimates all unknowns — mixing weights, component parameters, and even the number of components — through posterior inference. It extends classical mixture analysis by placing priors on every parameter and quantifying uncertainty over latent group assignments rather than treating them as fixed.