An Oracle Inequality for Quasi-Bayesian Non-Negative Matrix Factorization
arXiv:1601.01345v417 citations
Originality Synthesis-oriented
AI Analysis
This provides theoretical foundations for quasi-Bayesian methods in NMF, which is incremental as it extends existing theory to a more general class of priors.
The paper tackles the theoretical understanding of quasi-Bayesian aggregation methods in non-negative matrix factorization by deriving an oracle inequality for an aggregated estimator, showing how the prior distribution affects the convergence rate.
The aim of this paper is to provide some theoretical understanding of quasi-Bayesian aggregation methods non-negative matrix factorization. We derive an oracle inequality for an aggregated estimator. This result holds for a very general class of prior distributions and shows how the prior affects the rate of convergence.