tntorch: Tensor Network Learning with PyTorch

Mikhail Usvyatsov, Rafael Ballester-Ripoll, Konrad Schindler.

Year: 2022, Volume: 23, Issue: 208, Pages: 1−6


Abstract

We present tntorch, a tensor learning framework that supports multiple decompositions (including Candecomp/Parafac, Tucker, and Tensor Train) under a unified interface. With our library, the user can learn and handle low-rank tensors with automatic differentiation, seamless GPU support, and the convenience of PyTorch's API. Besides decomposition algorithms, tntorch implements differentiable tensor algebra, rank truncation, cross-approximation, batch processing, comprehensive tensor arithmetics, and more.

PDF BibTeX code