Corpus ID: 29989140

Tensor Train decomposition on TensorFlow (T3F)

@article{Novikov2020TensorTD,
  title={Tensor Train decomposition on TensorFlow (T3F)},
  author={Alexander Novikov and Pavel Izmailov and Valentin Khrulkov and Michael Figurnov and I. Oseledets},
  journal={J. Mach. Learn. Res.},
  year={2020},
  volume={21},
  pages={30:1-30:7}
}
Tensor Train decomposition is used across many branches of machine learning, but until now it lacked an implementation with GPU support, batch processing, automatic differentiation, and versatile functionality for Riemannian optimization framework, which takes in account the underlying manifold structure in order to construct efficient optimization methods. In this work, we propose a library that aims to fix it and makes machine learning papers that rely on Tensor Train decomposition easier to… Expand
25 Citations
Low Rank Tensor Completion for Multiway Visual Data
  • 48
  • PDF
Locally orderless tensor networks for classifying two- and three-dimensional medical images
  • 1
  • PDF
Performance of low-rank approximations in tensor train format (TT-SVD) for large dense tensors
  • PDF
PASTA: A Parallel Sparse Tensor Algorithm Benchmark Suite
  • 8
  • PDF
Distributed Non-Negative Tensor Train Decomposition
  • 1
  • PDF
Training Neural Machine Translation (NMT) Models using Tensor Train Decomposition on TensorFlow (T3F)
  • PDF
...
1
2
3
...

References

SHOWING 1-10 OF 35 REFERENCES
Supervised Learning with Tensor Networks
  • 137
  • PDF
TensorLy: Tensor Learning in Python
  • 134
  • PDF
Putting MRFs on a Tensor Train
  • 19
  • PDF
mpnum: A matrix product representation library for Python
  • 11
  • PDF
Tensor-Train Decomposition
  • I. Oseledets
  • Mathematics, Computer Science
  • SIAM J. Sci. Comput.
  • 2011
  • 1,141
Tensorizing Neural Networks
  • 459
  • PDF
Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
  • 501
  • PDF
Tensor-Train Recurrent Neural Networks for Video Classification
  • 101
  • PDF
A literature survey of low‐rank tensor approximation techniques
  • 475
  • PDF
...
1
2
3
4
...