Nonparametric Bayesian robustness
نویسندگان
چکیده
A new, nonparametric, approach to Bayesian robustness is presented. Whereas many studies in Bayesian robustness have dealt with a parametric sampling distribution, considering classes of prior distributions on the parameters, here we assume that the sampling distribution comes from a Dirichlet process with a parameter η = βα, with β > 0 and α being a probability measure, specified with uncertainty.
منابع مشابه
Bayesian Nonparametric and Parametric Inference
This paper reviews Bayesian Nonparametric methods and discusses how parametric predictive densities can be constructed using nonparametric ideas.
متن کاملInfinite Latent Harmonic Allocation: A Nonparametric Bayesian Approach to Multipitch Analysis
Maximum a posteriori estimation (MAP) Point estimates Manually specified Manually specified Modest Classical Bayesian estimation Posterior distributions Manually specified Manually specified Good (1) Nonparametric Bayesian estimation Posterior distributions Posterior distributions ―――― Excellent (2) Hierarchical Posterior distributions ―――― Posterior distributions Excellent Parameters Complexit...
متن کاملSome Results on Nonparametric Bayesian Robustness
As the parameter of a Dirichlet process varies in a class, we propose and compute a global sensitivity measure based on the Hellinger distance and we find optimal Bayesian estimators (under different criteria) of the random distribution function.
متن کاملNonparametric Bayesian Clustering Ensembles
Forming consensus clusters from multiple input clusterings can improve accuracy and robustness. Current clustering ensemble methods require specifying the number of consensus clusters. A poor choice can lead to under or over fitting. This paper proposes a nonparametric Bayesian clustering ensemble (NBCE) method, which can discover the number of clusters in the consensus clustering. Three infere...
متن کاملNonparametric Bayesian Models for Machine Learning
Nonparametric Bayesian Models for Machine Learning by Romain Jean Thibaux Doctor of Philosophy in Computer Science and the Designated Emphasis in Communication, Computation and Statistics University of California, Berkeley Professor Michael I. Jordan, Chair This thesis presents general techiques for inference in various nonparametric Bayesian models, furthers our understanding of the stochastic...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010