Local Exchangeability
arXiv:1906.09507 · doi:10.3150/22-BEJ1533
Abstract
Exchangeability -- in which the distribution of an infinite sequence is invariant to reorderings of its elements -- implies the existence of a simple conditional independence structure that may be leveraged in the design of statistical models and inference procedures. In this work, we study a relaxation of exchangeability in which this invariance need not hold precisely. We introduce the notion of local exchangeability -- where swapping data associated with nearby covariates causes a bounded change in the distribution. We prove that locally exchangeable processes correspond to independent observations from an underlying measure-valued stochastic process. Using this main probabilistic result, we show that the local empirical measure of a finite collection of observations provides an approximation of the underlying measure-valued process and Bayesian posterior predictive distributions. The paper concludes with applications of the main theoretical results to a model from Bayesian nonparametrics and covariate-dependent permutation tests.
References in corpus (8)
- Continuous Time Dynamic Topic Models
- Sparse graphs using exchangeable random measures
- Sparse exchangeable graphs and their limits via graphon processes
- Limit theorems for a class of identically distributed random variables
- The Class of Random Graphs Arising from Exchangeable Random Measures
- Edge-exchangeable graphs and sparsity
- On edge exchangeable random graphs
- Relational exchangeability