Deviance matrix factorization
From MaRDI portal
Abstract: We investigate a general matrix factorization for deviance-based data losses, extending the ubiquitous singular value decomposition beyond squared error loss. While similar approaches have been explored before, our method leverages classical statistical methodology from generalized linear models (GLMs) and provides an efficient algorithm that is flexible enough to allow for structural zeros via entry weights. Moreover, by adapting results from GLM theory, we provide support for these decompositions by (i) showing strong consistency under the GLM setup, (ii) checking the adequacy of a chosen exponential family via a generalized Hosmer-Lemeshow test, and (iii) determining the rank of the decomposition via a maximum eigenvalue gap method. To further support our findings, we conduct simulation studies to assess robustness to decomposition assumptions and extensive case studies using benchmark datasets from image face recognition, natural language processing, network analysis, and biomedical studies. Our theoretical and empirical results indicate that the proposed decomposition is more flexible, general, and robust, and can thus provide improved performance when compared to similar methods. To facilitate applications, an R package with efficient model fitting and family and rank determination is also provided.
Cites work
- A generalized least-square matrix decomposition
- A Logistic Factorization Model for Recommender Systems With Multinomial Responses
- A simple generalisation of the area under the ROC curve for multiple class classification problems
- Arbitrage, Factor Structure, and Mean-Variance Analysis on Large Asset Markets
- Bi-cross-validation of the SVD and the nonnegative matrix factorization
- Community structure in social and biological networks
- Dealing With Label Switching in Mixture Models
- Estimating Number of Factors by Adjusted Eigenvalues Thresholding
- Factor analysis with (mixed) observed and latent variables in the exponential family
- Generalised linear model selection by the predictive least quasi-deviance criterion
- Goodness of fit tests for the multiple logistic regression model
- scientific article; zbMATH DE number 1818892 (Why is no real title available?)
- scientific article; zbMATH DE number 47310 (Why is no real title available?)
- scientific article; zbMATH DE number 3458075 (Why is no real title available?)
- scientific article; zbMATH DE number 741107 (Why is no real title available?)
- scientific article; zbMATH DE number 6159604 (Why is no real title available?)
- Latent Space Approaches to Social Network Analysis
- Learning the parts of objects by non-negative matrix factorization
- Linear Model Selection by Cross-Validation
- Model Checks for Generalized Linear Models
- Nonparametric model checks for regression
- Pattern recognition and machine learning.
- Random Dot Product Graph Models for Social Networks
- Rejoinder
- Strong consistency of least squares estimates in multiple regression II
- Strong consistency of maximum quasi-likelihood estimators in generalized linear models with fixed and adaptive designs
Cited in
(3)
This page was built for publication: Deviance matrix factorization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6184929)
