t3f

t3f

Tensor Train decomposition on TensorFlow

Showing:

Popularity

Downloads/wk

0

GitHub Stars

190

Maintenance

Last Commit

5mos ago

Contributors

10

Package

Dependencies

0

License

MIT

Categories

Readme

Build Status Coverage Status

TensorFlow implementation of a library for working with Tensor Train (TT) decomposition which is also known as Matrix Product State (MPS).

Documentation

The documentation is available via readthedocs.

Comparison with other libraries

There are about a dozen other libraries implementing Tensor Train decomposition. The main difference between t3f and other libraries is that t3f has extensive support for Riemannian optimization and that it uses TensorFlow as backend and thus supports GPUs, automatic differentiation, and batch processing. For a more detailed comparison with other libraries, see the corresponding page in the docs.

Tests

nosetests  --logging-level=WARNING

Building documentation

The documentation is build by sphinx and hosted on readthedocs.org. To locally rebuild the documentation, install sphinx and compile the docs by

cd docs
make html

Citing

If you use T3F in your research work, we kindly ask you to cite the paper describing this library


@article{JMLR:v21:18-008,
  author  = {Alexander Novikov and Pavel Izmailov and Valentin Khrulkov and Michael Figurnov and Ivan Oseledets},
  title   = {Tensor Train Decomposition on TensorFlow (T3F)},
  journal = {Journal of Machine Learning Research},
  year    = {2020},
  volume  = {21},
  number  = {30},
  pages   = {1-7},
  url     = {http://jmlr.org/papers/v21/18-008.html}
}

Rate & Review

Great Documentation0
Easy to Use0
Performant0
Highly Customizable0
Bleeding Edge0
Responsive Maintainers0
Poor Documentation0
Hard to Use0
Slow0
Buggy0
Abandoned0
Unwelcoming Community0
100