Approximate method of variational Bayesian matrix factorization/completion with sparse prior

作者：Kawasumi Ryota; Takeda Koujin^*

来源：Journal of Statistical Mechanics: Theory and Experiment , 2018, 2018(5): 053404.

DOI：10.1088/1742-5468/aabc7d

• statistical inference
• learning theory
• spin glasses

We derive the analytical expression of a matrix factorization/ completion solution by the variational Bayes method, under the assumption that the observed matrix is originally the product of low-rank, dense and sparse matrices with additive noise. We assume the prior of a sparse matrix is a Laplace distribution by taking matrix sparsity into consideration. Then we use several approximations for the derivation of a matrix factorization/completion solution. By our solution, we also numerically evaluate the performance of a sparse matrix reconstruction in matrix factorization, and completion of a missing matrix element in matrix completion.

• 出版日期2018-5