ML Anthology

Tensor Train Decomposition on TensorFlow (T3F)

Alexander Novikov, Pavel Izmailov, Valentin Khrulkov, Michael Figurnov, Ivan Oseledets
MLOSS 2020 pp. 1-7
/mloss/2020/novikov2020jmlr-tensor/

Abstract

Tensor Train decomposition is used across many branches of machine learning. We present T3F—a library for Tensor Train decomposition based on TensorFlow. T3F supports GPU execution, batch processing, automatic differentiation, and versatile functionality for the Riemannian optimization framework, which takes into account the underlying manifold structure to construct efficient optimization methods. The library makes it easier to implement machine learning papers that rely on the Tensor Train decomposition. T3F includes documentation, examples and 94% test coverage.

PDF MLOSS Code Semantic Scholar

Cite

Text

Novikov et al. "Tensor Train Decomposition on TensorFlow (T3F)." Machine Learning Open Source Software, 2020.

Markdown

[Novikov et al. "Tensor Train Decomposition on TensorFlow (T3F)." Machine Learning Open Source Software, 2020.](https://mlanthology.org/mloss/2020/novikov2020jmlr-tensor/)

BibTeX

@article{novikov2020jmlr-tensor,
  title     = {{Tensor Train Decomposition on TensorFlow (T3F)}},
  author    = {Novikov, Alexander and Izmailov, Pavel and Khrulkov, Valentin and Figurnov, Michael and Oseledets, Ivan},
  journal   = {Machine Learning Open Source Software},
  year      = {2020},
  pages     = {1-7},
  volume    = {21},
  url       = {https://mlanthology.org/mloss/2020/novikov2020jmlr-tensor/}
}