An Oracle Inequality for Quasi-Bayesian Non-Negative Matrix Factorization
arXiv:1601.01345 · doi:10.3103/S1066530717010045
Abstract
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.
arXiv commentThis is the corrected version of the published paper P. Alquier, B. Guedj, An Oracle Inequality for Quasi-Bayesian Non-negative Matrix Factorization, Mathematical Methods of Statistics, 2017, vol. 26, no. 1, pp. 55-67. Since then Arnak Dalalyan (ENSAE) found a mistake in the proofs. We fixed the mistake at the price of a slightly different logarithmic term in the bound
References in corpus (6)
- An Alternating Direction Algorithm for Matrix Completion with Nonnegative Factors
- Factoring nonnegative matrices with linear programs
- Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
- Bayesian methods for low-rank matrix estimation: short survey and theoretical study
- A Bayesian Approach for Noisy Matrix Completion: Optimal Rate under General Sampling Distribution
- PAC-Bayesian Estimation and Prediction in Sparse Additive Models