One-dimensional Tensor Network Recovery

MaRDI QIDQ6506295arXivFDO

Authors Ziang Chen, Jianfeng Lu, Anru R. Zhang

Published in arXiv

Abstract: We study the recovery of the underlying graphs or permutations for tensors in tensor ring or tensor train format. Our proposed algorithms compare the matricization ranks after down-sampling, whose complexity is $O(dlogd)$ for $d$-th order tensors. We prove that our algorithms can almost surely recover the correct graph or permutation when tensor entries can be observed without noise. We further establish the robustness of our algorithms against observational noise. The theoretical results are validated by numerical experiments.

This page was built for publication: One-dimensional Tensor Network Recovery

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6506295)