Exchangeable Variable Models
نویسندگان
چکیده
A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations. We introduce exchangeable variable models (EVMs) as a novel class of probabilistic models whose basic building blocks are partially exchangeable sequences, a generalization of exchangeable sequences. We prove that a family of tractable EVMs is optimal under zeroone loss for a large class of functions, including parity and threshold functions, and strictly subsumes existing tractable independence-based model families. Extensive experiments show that EVMs outperform state of the art classifiers such as SVMs and probabilistic models which are solely based on independence assumptions.
منابع مشابه
Restricting exchangeable nonparametric distributions
Distributions over matrices with exchangeable rows and infinitely many columns are useful in constructing nonparametric latent variable models. However, the distribution implied by such models over the number of features exhibited by each data point may be poorly-suited for many modeling tasks. In this paper, we propose a class of exchangeable nonparametric priors obtained by restricting the do...
متن کاملDependence and Conditional Independence in Economic Models ∗
De Finetti’s Theorem asserts that a sequence of exchangeable variables are conditionally independent, that is, dependence under exchangeability is nothing but conditionally independence. However, de Finetti’s theorem is valid only with a infinite number of random variables, which makes this result unsuitable for application in many economic models. In this paper, we prove that dependence is con...
متن کاملExchangeable Equilibria, Part I: Symmetric Bimatrix Games
We introduce the notion of exchangeable equilibria of a symmetric bimatrix game, defined as those correlated equilibria in which players’ strategy choices are conditionally independently and identically distributed given some hidden variable. The set of these equilibria is convex and lies between the symmetric Nash equilibria and the symmetric correlated equilibria. The notion of exchangeable e...
متن کاملThe Phylogenetic Indian Buffet Process: A Non-Exchangeable Nonparametric Prior for Latent Features
Nonparametric Bayesian models are often based on the assumption that the objects being modeled are exchangeable. While appropriate in some applications (e.g., bag-ofwords models for documents), exchangeability is sometimes assumed simply for computational reasons; non-exchangeable models might be a better choice for applications based on subject matter. Drawing on ideas from graphical models an...
متن کاملClusters and Features from Combinatorial Stochastic Processes
In partitioning-‐-‐-‐a.k.a. clustering-‐-‐-‐data, we associate each data point with one and only one of some collection of groups called clusters or partition blocks. Here, we formally establish an analogous problem, called feature allocation, for associating data points with arbitrary non-‐negative integer numbers of groups, now called features or topics. Just as the exchangeable partit...
متن کامل