Global analytic solution of fully-observed variational Bayesian matrix factorization

MaRDI QIDQ5405239zbMATH OpenFDO

Authors Shinichi Nakajima, Masashi Sugiyama, S. Derin Babacan, Ryota Tomioka

Publication date 1 April 2014

Full work available at URL http://www.jmlr.org/papers/v14/nakajima13a.html

zbMATH Keywords

empirical Bayesmatrix factorizationmodel-induced regularizationprobabilistic PCAvariational Bayes

Mathematics Subject Classification ID

Factorization of matrices (15A23) Factor analysis and principal components; correspondence analysis (62H25)

Recommendations

• Theoretical analysis of Bayesian matrix factorization
• Approximate method of variational Bayesian matrix factorization/completion with sparse prior
• Condition for perfect dimensionality recovery by variational Bayesian PCA
• A note on variational Bayesian factor analysis
• Variational approximation error in non-negative matrix factorization

Cited in

(9)

• Reduced-order modeling of deep neural networks
• Cauchy noise loss for stochastic optimization of random matrix models via free deterministic equivalents
• Link sign prediction by variational Bayesian probabilistic matrix factorization with Student-\(t\) prior
• Condition for perfect dimensionality recovery by variational Bayesian PCA
• A note on variational Bayesian factor analysis
• Variational Bayesian sparse additive matrix factorization
• Approximate method of variational Bayesian matrix factorization/completion with sparse prior
• Empirical Bayes matrix factorization
• Theoretical analysis of Bayesian matrix factorization

This page was built for publication: Global analytic solution of fully-observed variational Bayesian matrix factorization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5405239)