Mutual Information for Low-Rank Even-Order Symmetric Tensor Factorization

04/09/2019

∙

by   Jean Barbier, et al.

∙

0

∙

share

We consider a statistical model for finite-rank symmetric tensor factorization and prove a single-letter variational expression for its mutual information when the tensor is of even order. The proof uses the adaptive interpolation method, for which rank-one matrix factorization is one of the first problem it was successfully applied to. We show how to extend the adaptive interpolation to finite-rank symmetric tensors of even order, which requires new ideas with respect to the proof for the rank-one case. We also underline where the proof falls short when dealing with odd-order tensors.