Mixtures and products in two graphical models
نویسندگان
چکیده
منابع مشابه
Learning Mixtures of Tree Graphical Models
We consider unsupervised estimation of mixtures of discrete graphical models, where the class variable is hidden and each mixture component can have a potentially different Markov graph structure and parameters over the observed variables. We propose a novel method for estimating the mixture components with provable guarantees. Our output is a tree-mixture model which serves as a good approxima...
متن کاملLearning High-Dimensional Mixtures of Graphical Models
We consider unsupervised estimation of mixtures of discrete graphical models, where the class variable corresponding to the mixture components is hidden and each mixture component over the observed variables can have a potentially different Markov graph structure and parameters. We propose a novel approach for estimating the mixture components, and our output is a tree-mixture model which serve...
متن کاملComputationally Efficient Methods for Selecting Among Mixtures of Graphical Models
We describe computationally efficient methods for Bayesian model selection. The methods select among mixtures in which each component is a directed acyclic graphical model (mixtures of DAGs or MDAGs), and can be applied to data sets in which some of the random variables are not always observed. The model-selection criterion that we consider is the posterior probability of the model (structure) ...
متن کاملHyperbolic Models of Homogeneous Two-Fluid Mixtures
Abstract. One derives the governing equations and the Rankine Hugoniot conditions for a mixture of two miscible fluids using an extended form of Hamilton’s principle of least action. The Lagrangian is constructed as the difference between the kinetic energy and a potential depending on the relative velocity of components. To obtain the governing equations and the jump conditions one uses two re...
متن کاملAppendix to “ Bayesian Mixtures of Autoregressive Models ” published in the Journal of Computational and Graphical Statistics
j=1 |X ′ pZjXp + c−1X ′ pXp|b −aj j , where Zj = diag(ztjpr, t = P + 1, . . . , n). Note that ztjpr takes on the same value (zero or one) for all t ∈ {1 + (s − 1)L, . . . , sL}. The expressions for aj and bj are aj = 1 2 ∑n t=P+1 zjtpr + α and bj = 1 2 yMjy ∗ + β, where Mj = Zj − ZjXp(X ′ pZjXp + c−1X ′ pXp) −1X ′ pZj. 3. Let psjpr = sL ∏ t=1+(s−1)L p(yt|xt−1;φjpr, σ jpr). Draw the indicators f...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Algebraic Statistics
سال: 2018
ISSN: 1309-3452
DOI: 10.18409/jas.v9i1.90