Legendre Decomposition for Tensors
Abstract
We present a novel nonnegative tensor decomposition method, called Legendre decomposition, which factorizes an input tensor into a multiplicative combination of parameters. Thanks to the well-developed theory of information geometry, the reconstructed tensor is unique and always minimizes the KL divergence from an input tensor. We empirically show that Legendre decomposition can more accurately reconstruct tensors than other nonnegative tensor decomposition methods.
Cite
Text
Sugiyama et al. "Legendre Decomposition for Tensors." Neural Information Processing Systems, 2018.Markdown
[Sugiyama et al. "Legendre Decomposition for Tensors." Neural Information Processing Systems, 2018.](https://mlanthology.org/neurips/2018/sugiyama2018neurips-legendre/)BibTeX
@inproceedings{sugiyama2018neurips-legendre,
title = {{Legendre Decomposition for Tensors}},
author = {Sugiyama, Mahito and Nakahara, Hiroyuki and Tsuda, Koji},
booktitle = {Neural Information Processing Systems},
year = {2018},
pages = {8811-8821},
url = {https://mlanthology.org/neurips/2018/sugiyama2018neurips-legendre/}
}