Variational inference for probabilistic Poisson PCA

DOI10.1214/18-AOAS1177zbMATH Open1412.62194arXiv1703.06633MaRDI QIDQ1728678FDOQ1728678

Authors: Julien Chiquet, Mahendra Mariadassou, Stéphane Robin 

Publication date: 25 February 2019

Published in: The Annals of Applied Statistics (Search for Journal in Brave)

Abstract: Many application domains such as ecology or genomics have to deal with multivariate non Gaussian observations. A typical example is the joint observation of the respective abundances of a set of species in a series of sites, aiming to understand the co-variations between these species. The Gaussian setting provides a canonical way to model such dependencies, but does not apply in general. We consider here the multivariate exponential family framework for which we introduce a generic model with multivariate Gaussian latent variables. We show that approximate maximum likelihood inference can be achieved via a variational algorithm for which gradient descent easily applies. We show that this setting enables us to account for covariates and offsets. We then focus on the case of the Poisson-lognormal model in the context of community ecology. We demonstrate the efficiency of our algorithm on microbial ecology datasets. We illustrate the importance of accounting for the effects of covariates to better understand interactions between species.

Full work available at URL: https://arxiv.org/abs/1703.06633

Recommendations

• Variational Gaussian approximation for Poisson data
• Theory of Gaussian variational approximation for a Poisson mixed model
• Variational inference for Dirichlet process mixtures
• Variational inference in nonconjugate models
• scientific article; zbMATH DE number 1931821
• Expectation propagation for Poisson data
• Poisson approximation of multivariate Poisson mixtures
• Variational Bayesian functional PCA
• scientific article

zbMATH Keywords

count datavariational inferencePoisson-lognormal modelprobabilistic PCAmultivariate exponential family framework

Mathematics Subject Classification ID

Factor analysis and principal components; correspondence analysis (62H25) Applications of statistics to environmental and related topics (62P12)

Cites Work

• A penalized matrix decomposition, with applications to sparse principal components and canonical correlation analysis
• \(e\)PCA: high dimensional exponential family PCA
• Estimating the dimension of a model
• Graphical models, exponential families, and variational inference
• ggplot2. Elegant graphics for data analysis
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• The multivariate Poisson-log normal distribution
• Title not available (Why is that?)
• Probabilistic Principal Component Analysis
• Title not available (Why is that?)
• A class of globally convergent optimization methods based on conservative convex separable approximations
• Theory of Gaussian variational approximation for a Poisson mixed model
• EM Algorithm for Mixed Poisson and Other Discrete Distributions
• Poisson noise reduction with non-local PCA
• Title not available (Why is that?)

Cited In (10)

• Low-rank model with covariates for count data with missing values
• A literature review of (Sparse) exponential family PCA
• On some limitations of probabilistic models for dimension‐reduction: Illustration in the case of probabilistic formulations of partial least squares
• Poisson PCA: Poisson measurement error corrected PCA, with application to microbiome data
• Anomaly and novelty detection for robust semi-supervised learning
• Empirical Bayes Poisson matrix completion
• A Randomized Pairwise Likelihood Method for Complex Statistical Inferences
• High-dimensional overdispersed generalized factor model with application to single-cell sequencing data analysis
• Greedy clustering of count data through a mixture of multinomial PCA
• Model-Based Microbiome Data Ordination: A Variational Approximation Approach

Uses Software

• R
• nloptr
• ggplot2
• NLopt
• PMA
• ePCA
• GPSeq
• GitHub

This page was built for publication: Variational inference for probabilistic Poisson PCA

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1728678)