NeurIPS 2018spotlight24 citations
Legendre Decomposition for Tensors
Mahito Sugiyama, Hiroyuki Nakahara, Koji Tsuda
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.
BibTeX
@inproceedings{NEURIPS2018_56a3107c,
author = {Sugiyama, Mahito and Nakahara, Hiroyuki and Tsuda, Koji},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Legendre Decomposition for Tensors},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/56a3107cad6611c8337ee36d178ca129-Paper.pdf},
volume = {31},
year = {2018}
}