Priors on exchangeable directed graphs
نویسندگان
چکیده
Directed graphs occur throughout statistical modeling of networks, and exchangeability is a natural assumption when the ordering of vertices does not matter. There is a deep structural theory for exchangeable undirected graphs, which extends to the directed case via measurable objects known as digraphons. Using digraphons, we first show how to construct models for exchangeable directed graphs, including special cases such as tournaments, linear orderings, directed acyclic graphs, and partial orderings. We then show how to construct priors on digraphons via the infinite relational digraphon model (di-IRM), a new Bayesian nonparametric block model for exchangeable directed graphs, and demonstrate inference on synthetic data. MSC 2010 subject classifications: Primary 60G09, 05C20; secondary 62F15, 62G05.
منابع مشابه
Random function priors for exchangeable arrays with applications to graphs and relational data
A fundamental problem in the analysis of structured relational data like graphs, networks, databases, and matrices is to extract a summary of the common structure underlying relations between individual entities. Relational data are typically encoded in the form of arrays; invariance to the ordering of rows and columns corresponds to exchangeable arrays. Results in probability theory due to Ald...
متن کاملOn independent domination numbers of grid and toroidal grid directed graphs
A subset $S$ of vertex set $V(D)$ is an {em indpendent dominating set} of $D$ if $S$ is both an independent and a dominating set of $D$. The {em indpendent domination number}, $i(D)$ is the cardinality of the smallest independent dominating set of $D$. In this paper we calculate the independent domination number of the { em cartesian product} of two {em directed paths} $P_m$ and $P_n$ for arbi...
متن کاملBayesian Modeling of Dependency Trees Using Hierarchical Pitman-Yor Priors
Recent work in hierarchical priors for language modeling [MacKay and Peto, 1994, Teh, 2006, Goldwater et al., 2006] has shown significant advantages to Bayesian methods in NLP. But the issue of sparse conditioning contexts is ubiquitous in NLP, and these smoothing ideas can be applied more broadly to extend the reach of Bayesian modeling in natural language. For example, a useful representation...
متن کاملOn exchangeable random variables and the statistics of large graphs and hypergraphs
De Finetti’s classical result of [18] identifying the law of an exchangeable family of random variables as a mixture of i.i.d. laws was extended to structure theorems for more complex notions of exchangeability by Aldous [1, 2, 3], Hoover [41, 42], Kallenberg [44] and Kingman [47]. On the other hand, such exchangeable laws were first related to questions from combinatorics in an independent ana...
متن کامل