Asymptotic Accuracy of Distribution-Based Estimation for Latent Variables

04/10/2012
by   Keisuke Yamazaki, et al.
0

Hierarchical statistical models are widely employed in information science and data engineering. The models consist of two types of variables: observable variables that represent the given data and latent variables for the unobservable labels. An asymptotic analysis of the models plays an important role in evaluating the learning process; the result of the analysis is applied not only to theoretical but also to practical situations, such as optimal model selection and active learning. There are many studies of generalization errors, which measure the prediction accuracy of the observable variables. However, the accuracy of estimating the latent variables has not yet been elucidated. For a quantitative evaluation of this, the present paper formulates distribution-based functions for the errors in the estimation of the latent variables. The asymptotic behavior is analyzed for both the maximum likelihood and the Bayes methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/09/2013

Accuracy of Latent-Variable Estimation in Bayesian Semi-Supervised Learning

Hierarchical probabilistic models, such as Gaussian mixture models, are ...
research
10/07/2017

Nonsparse learning with latent variables

As a popular tool for producing meaningful and interpretable models, lar...
research
05/15/2012

Asymptotic Accuracy of Bayes Estimation for Latent Variables with Redundancy

Hierarchical parametric models consisting of observable and latent varia...
research
01/16/2013

Model Criticism of Bayesian Networks with Latent Variables

The application of Bayesian networks (BNs) to cognitive assessment and i...
research
02/11/2019

Error Analysis on Graph Laplacian Regularized Estimator

We provide a theoretical analysis of the representation learning problem...
research
06/20/2018

Estimation of component reliability in repairable series systems with masked cause of failure by means of latent variables

In this work, we propose two methods, a Bayesian and a maximum likelihoo...
research
10/16/2012

Latent Composite Likelihood Learning for the Structured Canonical Correlation Model

Latent variable models are used to estimate variables of interest quanti...

Please sign up or login with your details

Forgot password? Click here to reset