The Poisson transform for unnormalised statistical models

DOI10.1007/S11222-015-9559-4zbMATH Open1332.62364arXiv1406.2839OpenAlexW1508045242MaRDI QIDQ5963779FDOQ5963779

Simon Barthelmé, Nicolas Chopin

Publication date: 23 February 2016

Published in: Statistics and Computing (Search for Journal in Brave)

Abstract: Contrary to standard statistical models, unnormalised statistical models only specify the likelihood function up to a constant. While such models are natural and popular, the lack of normalisation makes inference much more difficult. Here we show that inferring the parameters of a unnormalised model on a space $Omega$ can be mapped onto an equivalent problem of estimating the intensity of a Poisson point process on $Omega$. The unnormalised statistical model now specifies an intensity function that does not need to be normalised. Effectively, the normalisation constant may now be inferred as just another parameter, at no loss of information. The result can be extended to cover non-IID models, which includes for example unnormalised models for sequences of graphs (dynamical graphs), or for sequences of binary vectors. As a consequence, we prove that unnormalised parameteric inference in non-IID models can be turned into a semi-parametric estimation problem. Moreover, we show that the noise-contrastive divergence of Gutmann & Hyv"arinen (2012) can be understood as an approximation of the Poisson transform, and extended to non-IID settings. We use our results to fit spatial Markov chain models of eye movements, where the Poisson transform allows us to turn a highly non-standard model into vanilla semi-parametric logistic regression.

Full work available at URL: https://arxiv.org/abs/1406.2839

Recommendations

• scientific article; zbMATH DE number 6276120
• Statistical inference with unnormalized discrete models and localized homogeneous divergences
• Noise contrastive estimation: asymptotic properties, formal comparison with MC-MLE
• Some extensions of score matching
• Estimation of non-normalized statistical models by score matching

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Inference from spatial processes (62M30) Point processes (e.g., Poisson, Cox, Hawkes processes) (60G55)

Cites Work

• Generalized additive models. An introduction with R.
• The elements of statistical learning. Data mining, inference, and prediction
• Asymptotic Statistics
• Fast Stable Restricted Maximum Likelihood and Marginal Likelihood Estimation of Semiparametric Generalized Linear Models
• An efficient Markov chain Monte Carlo method for distributions with intractable normalising constants
• Title not available (Why is that?)
• Training Products of Experts by Minimizing Contrastive Divergence
• On Russian roulette estimates for Bayesian inference with doubly-intractable likelihoods
• Title not available (Why is that?)
• Maximum likelihood estimation for spatial models by Markov chain Monte Carlo stochastic approximation
• Posterior Sampling When the Normalizing Constant is Unknown
• Justifying and Generalizing Contrastive Divergence
• Spatial logistic regression and change-of-support in Poisson point processes
• An efficient learning procedure for deep Boltzmann machines
• Logistic regression for spatial Gibbs point processes

Cited In (3)

• Likelihood-free inference via classification
• Noise contrastive estimation: asymptotic properties, formal comparison with MC-MLE
• On the classical choice of variance stabilizing transformations and an application for a Poisson variate

Uses Software

• gamair

This page was built for publication: The Poisson transform for unnormalised statistical models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5963779)