TensorLy: Tensor Learning in Python

TL;DR

TensorLy is a Python library that provides a high-level API for tensor operations and deep tensorized neural networks, supporting multiple backends and scalable computations for both research and commercial use.

Contribution

It introduces a unified, flexible, and scalable Python library for tensor methods that integrates with major scientific and deep learning frameworks.

Findings

Supports multiple backends including NumPy, PyTorch, TensorFlow, MXNet, CuPy

Enables scalable tensor computations on CPU and GPU clusters

Facilitates design and training of deep tensorized neural networks

Abstract

Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of machine learning and data analysis, tensor methods have been gaining increasing traction. However, software support for tensor operations is not on the same footing. In order to bridge this gap, we have developed \emph{TensorLy}, a high-level API for tensor methods and deep tensorized neural networks in Python. TensorLy aims to follow the same standards adopted by the main projects of the Python scientific community, and seamlessly integrates with them. Its BSD license makes it suitable for both academic and commercial applications. TensorLy's backend system allows users to perform computations with NumPy, MXNet, PyTorch, TensorFlow and CuPy. They can be scaled on multiple CPU or GPU machines. In addition, using the deep-learning frameworks as backend allows users to easily design and train deep tensorized neural networks. TensorLy is available at https://github.com/tensorly/tensorly