Barbier, JeanLuneau, ClementMacris, Nicolas2020-07-042020-07-042020-07-042019-01-0110.1109/ITW44776.2019.8989408https://infoscience.epfl.ch/handle/20.500.14299/169803WOS:000540384500016We 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 problems to which it was successfully applied. 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.text::conference output::conference proceedings::conference paper