An Oracle Inequality for Quasi-Bayesian Non-Negative Matrix Factorization

01/06/2016
by   Pierre Alquier, et al.
0

The aim of this paper is to provide some theoretical understanding of Bayesian non-negative matrix factorization methods. We derive an oracle inequality for a quasi-Bayesian estimator. This result holds for a very general class of prior distributions and shows how the prior affects the rate of convergence. We illustrate our theoretical results with a short numerical study along with a discussion on existing implementations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/16/2019

Non-negative matrix factorization based on generalized dual divergence

A theoretical framework for non-negative matrix factorization based on g...
research
04/11/2021

A Non-Negative Matrix Factorization Game

We present a novel game-theoretic formulation of Non-Negative Matrix Fac...
research
09/24/2021

Bayesian non-parametric non-negative matrix factorization for pattern identification in environmental mixtures

Environmental health researchers may aim to identify exposure patterns t...
research
11/30/2022

Quasi Non-Negative Quaternion Matrix Factorization with Application to Color Face Recognition

To address the non-negativity dropout problem of quaternion models, a no...
research
09/13/2017

Asymptotic Bayesian Generalization Error in a General Stochastic Matrix Factorization for Markov Chain and Bayesian Network

Stochastic matrix factorization (SMF) can be regarded as a restriction o...
research
08/12/2018

Neural System Identification with Spike-triggered Non-negative Matrix Factorization

Neuronal circuits formed in the brain are complex with intricate connect...
research
08/12/2018

Characterizing Neuronal Circuits with Spike-triggered Non-negative Matrix Factorization

Neuronal circuits formed in the brain are complex with intricate connect...

Please sign up or login with your details

Forgot password? Click here to reset