Publication:
Tntorch: Tensor Network Learning with PyTorch

Thumbnail Image
Files
Tensor Network Learning with PyTorch.pdf (843.47 KB)
Date
2022
Authors
Advisor
Court
Journal Title
Journal ISSN
Volume Title
Publisher
JMLR
Defense Date
Citation
Research Projects
Organizational Units
Journal Issue
URI
https://hdl.handle.net/20.500.14417/3701
DOI
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, crossapproximation, batch processing, comprehensive tensor arithmetics, and more.
Unesco subjects
License
Attribution 4.0 International
School
IE School of Science & Technology
Center
Keywords
Citation
Usvyatsov, M., Ballester-Ripoll, R., & Schindler, K. (2022). tntorch: Tensor network learning with PyTorch. Journal of Machine Learning Research, 23(208), 1-6.
Collections
Research Articles