Bayesian methods for low-rank matrix estimation: short survey and theoretical study

DOI10.1007/978-3-642-40935-6_22MaRDI QIDQ2859226zbMATH OpenOpenAlexFDO

Authors Pierre Alquier

Publication date 6 November 2013

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1306.3862

zbMATH Keywords

Bayesian inferencematrix completionoracle inequalitiesreduced-rank regressioncollaborative filteringPAC-Bayesian bounds

Mathematics Subject Classification ID

Bayesian inference (62F15) Estimation in multivariate analysis (62H12)

Abstract: The problem of low-rank matrix estimation recently received a lot of attention due to challenging applications. A lot of work has been done on rank-penalized methods and convex relaxation, both on the theoretical and applied sides. However, only a few papers considered Bayesian estimation. In this paper, we review the different type of priors considered on matrices to favour low-rank. We also prove that the obtained Bayesian estimators, under suitable assumptions, enjoys the same optimality properties as the ones based on penalization.

Recommendations

• A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
• Bayesian rank penalization
• Estimation of high-dimensional low-rank matrices
• Robust matrix completion
• Rank penalized estimators for high-dimensional matrices

Cited in

(17)

• Numerical comparisons between Bayesian and frequentist low-rank matrix completion: estimation accuracy and uncertainty quantification
• On the exponentially weighted aggregate with the Laplace prior
• Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications
• Bayesian sparse reduced rank multivariate regression
• Matrix factorization for multivariate time series analysis
• Inference on low-rank data matrices with applications to microarray data
• Sparse Bayesian Methods for Low-Rank Matrix Estimation
• Exponential weights in multivariate regression and a low-rankness favoring prior
• A reduced-rank approach to predicting multiple binary responses through machine learning
• Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
• Bayesian rank penalization
• An oracle inequality for quasi-Bayesian nonnegative matrix factorization
• Bootstrap-based regularization for low-rank matrix estimation
• User-friendly Introduction to PAC-Bayes Bounds
• On the properties of variational approximations of Gibbs posteriors
• A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
• A fully Bayesian approach to sparse reduced-rank multivariate regression

This page was built for publication: Bayesian methods for low-rank matrix estimation: short survey and theoretical study

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2859226)