DeepAI AI Chat
Log In Sign Up

Curved factor analysis with the Ellipsoid-Gaussian distribution

by   Hanyu Song, et al.

There is a need for new models for characterizing dependence in multivariate data. The multivariate Gaussian distribution is routinely used, but cannot characterize nonlinear relationships in the data. Most non-linear extensions tend to be highly complex; for example, involving estimation of a non-linear regression model in latent variables. In this article, we propose a relatively simple class of Ellipsoid-Gaussian multivariate distributions, which are derived by using a Gaussian linear factor model involving latent variables having a von Mises-Fisher distribution on a unit hyper-sphere. We show that the Ellipsoid-Gaussian distribution can flexibly model curved relationships among variables with lower-dimensional structures. Taking a Bayesian approach, we propose a hybrid of gradient-based geodesic Monte Carlo and adaptive Metropolis for posterior sampling. We derive basic properties and illustrate the utility of the Ellipsoid-Gaussian distribution on a variety of simulated and real data applications.


page 1

page 2

page 3

page 4


Bayesian neural networks and dimensionality reduction

In conducting non-linear dimensionality reduction and feature learning, ...

Estimating densities with nonlinear support using Fisher-Gaussian kernels

Current tools for multivariate density estimation struggle when the dens...

Geostatistics in the presence of multivariate complexities: comparison of multi-Gaussian transforms

Geostatistical simulation of two or more continuous variables is a commo...

Identifiability of latent-variable and structural-equation models: from linear to nonlinear

An old problem in multivariate statistics is that linear Gaussian models...

The joint projected normal and skew-normal: a distribution for poly-cylindrical data

The contribution of this work is the introduction of a multivariate circ...

Variational Filtering with Copula Models for SLAM

The ability to infer map variables and estimate pose is crucial to the o...

Scalable Bayesian Network Structure Learning with Splines

A Bayesian Network (BN) is a probabilistic graphical model consisting of...