CaltechAUTHORS
  A Caltech Library Service

TensorLy: Tensor Learning in Python

Kossaifi, Jean and Panagakis, Yannis and Anandkumar, Animashree and Pantic, Maja (2019) TensorLy: Tensor Learning in Python. Journal of Machine Learning Research, 20 (26). pp. 1-6. ISSN 1533-7928. http://resolver.caltech.edu/CaltechAUTHORS:20190228-133230688

[img] PDF - Published Version
Creative Commons Attribution.

444Kb
[img] PDF - Submitted Version
See Usage Policy.

381Kb

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20190228-133230688

Abstract

Tensors are higher-order extensions of matrices. While matrix methods form the cornerstone of traditional 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 TensorLy, a Python library that provides a high-level API for tensor methods and deep tensorized neural networks. TensorLy aims to follow the same standards adopted by the main projects of the Python scientific community, and to seamlessly integrate with them. Its BSD license makes it suitable for both academic and commercial applications. TensorLy's backend system allows users to perform computations with several libraries such as NumPy or PyTorch to name but a few. They can be scaled on multiple CPU or GPU machines. In addition, using the deep-learning frameworks as backend allows to easily design and train deep tensorized neural networks. TensorLy is available at https://github.com/tensorly/tensorly


Item Type:Article
Related URLs:
URLURL TypeDescription
http://www.jmlr.org/papers/v20/18-277.htmlPublisherArticle
https://arxiv.org/abs/1610.09555arXivDiscussion Paper
https://github.com/tensorly/tensorlyRelated ItemCode
Additional Information:© 2019 Jean Kossai, Yannis Panagakis, Anima Anandkumar and Maja Pantic. License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided at http://jmlr.org/papers/v20/18-277.html. Submitted 5/18; Revised 10/18; Published 2/19.
Record Number:CaltechAUTHORS:20190228-133230688
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20190228-133230688
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:93356
Collection:CaltechAUTHORS
Deposited By: Tony Diaz
Deposited On:28 Feb 2019 21:39
Last Modified:28 Feb 2019 21:39

Repository Staff Only: item control page