English

The Layered Structure of Tensor Estimation and its Mutual Information

Information Theory 2018-11-28 v3 Disordered Systems and Neural Networks Mathematical Physics math.IT math.MP

Abstract

We consider rank-one non-symmetric tensor estimation and derive simple formulas for the mutual information. We start by the order 2 problem, namely matrix factorization. We treat it completely in a simpler fashion than previous proofs using a new type of interpolation method developed in [1]. We then show how to harness the structure in "layers" of tensor estimation in order to obtain a formula for the mutual information for the order 3 problem from the knowledge of the formula for the order 2 problem, still using the same kind of interpolation. Our proof technique straightforwardly generalizes and allows to rigorously obtain the mutual information at any order in a recursive way.

Keywords

Cite

@article{arxiv.1709.10368,
  title  = {The Layered Structure of Tensor Estimation and its Mutual Information},
  author = {Jean Barbier and Nicolas Macris and Léo Miolane},
  journal= {arXiv preprint arXiv:1709.10368},
  year   = {2018}
}

Comments

55th Annual Allerton Conference on Communication, Control, and Computing, 2017

R2 v1 2026-06-22T21:58:51.067Z