tntorch: Tensor Network Learning with PyTorch
This is an incremental contribution for researchers and practitioners in machine learning and data analysis who need a flexible and high-performance tool for tensor computations.
The authors introduced tntorch, a tensor learning framework that unifies multiple tensor decompositions and provides GPU support and automatic differentiation within PyTorch, enabling efficient low-rank tensor handling and algebra.
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.