Tntorch: Tensor Network Learning with PyTorch

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.

Cite

Text

Usvyatsov et al. "Tntorch: Tensor Network Learning with PyTorch." Journal of Machine Learning Research, 2022.

Markdown

[Usvyatsov et al. "Tntorch: Tensor Network Learning with PyTorch." Journal of Machine Learning Research, 2022.](https://mlanthology.org/jmlr/2022/usvyatsov2022jmlr-tntorch/)

BibTeX

@article{usvyatsov2022jmlr-tntorch,
  title     = {{Tntorch: Tensor Network Learning with PyTorch}},
  author    = {Usvyatsov, Mikhail and Ballester-Ripoll, Rafael and Schindler, Konrad},
  journal   = {Journal of Machine Learning Research},
  year      = {2022},
  pages     = {1-6},
  volume    = {23},
  url       = {https://mlanthology.org/jmlr/2022/usvyatsov2022jmlr-tntorch/}
}