An oracle inequality for quasi-Bayesian nonnegative matrix factorization
From MaRDI portal
Publication:1678528
DOI10.3103/S1066530717010045zbMath1381.62222arXiv1601.01345OpenAlexW3103546337MaRDI QIDQ1678528
Pierre Alquier, Benjamin Guedj
Publication date: 17 November 2017
Published in: Mathematical Methods of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1601.01345
Multivariate analysis (62H99) Robustness and adaptive procedures (parametric inference) (62F35) Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05)
Related Items
Unnamed Item ⋮ Exponential weights in multivariate regression and a low-rankness favoring prior ⋮ Bayesian mean-parameterized nonnegative binary matrix factorization ⋮ Matrix factorization for multivariate time series analysis ⋮ A quasi-Bayesian perspective to online clustering ⋮ Simultaneous dimension reduction and clustering via the NMF-EM algorithm
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers
- Concentration inequalities for the exponential weighting method
- An alternating direction algorithm for matrix completion with nonnegative factors
- Aggregation by exponential weighting, sharp PAC-Bayesian bounds and sparsity
- PAC-Bayesian high dimensional bipartite ranking
- Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
- PAC-Bayesian estimation and prediction in sparse additive models
- An introduction to variational methods for graphical models
- A Bayesian approach for noisy matrix completion: optimal rate under general sampling distribution
- Document clustering using nonnegative matrix factorization
- Bayesian Methods for Low-Rank Matrix Estimation: Short Survey and Theoretical Study
- A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion
- On the properties of variational approximations of Gibbs posteriors
- Information Theory and Mixing Least-Squares Regressions
- Nonnegative Matrix Factorization with the Itakura-Saito Divergence: With Application to Music Analysis
- NeNMF: An Optimal Gradient Method for Nonnegative Matrix Factorization
- Separation of Non-Negative Mixture of Non-Negative Sources Using a Bayesian Approach and MCMC Sampling
- Bayesian assessment of dimensionality in reduced rank regression
- Fast Projection‐Based Methods for the Least Squares Nonnegative Matrix Approximation Problem
- A Generalized Least-Square Matrix Decomposition
- Learning the parts of objects by non-negative matrix factorization
- A General Framework for Updating Belief Distributions
- Aggregation by Exponential Weighting and Sharp Oracle Inequalities
- Projected Gradient Methods for Nonnegative Matrix Factorization
This page was built for publication: An oracle inequality for quasi-Bayesian nonnegative matrix factorization
