AISTATS 2024poster5 citations

The AL$\ell_0$CORE Tensor Decomposition for Sparse Count Data

John Hood, Aaron J. Schein

Abstract

This paper introduces AL$\ell_0$CORE, a new form of probabilistic non-negative tensor decomposition. AL$\ell_0$CORE is a Tucker decomposition that constrains the number of non-zero elements (i.e., the $\ell_0$-norm) of the core tensor to be at most $Q$. While the user dictates the total budget $Q$, the locations and values of the non-zero elements are latent variables allocated across the core tensor during inference. AL$\ell_0$CORE—i.e., allocated $\ell_0$-constrained core—thus enjoys both the computational tractability of canonical polyadic (CP) decomposition and the qualitatively appealing latent structure of Tucker. In a suite of real-data experiments, we demonstrate that AL$\ell_0$CORE typically requires only tiny fractions (e.g., 1%) of the core to achieve the same results as Tucker at a correspondingly small fraction of the cost.

BibTeX
@InProceedings{pmlr-v238-hood24a,
  title = 	 {The {AL$\ell_0$CORE} Tensor Decomposition for Sparse Count Data},
  author =       {Hood, John and Schein, Aaron J.},
  booktitle = 	 {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {4654--4662},
  year = 	 {2024},
  editor = 	 {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
  volume = 	 {238},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {02--04 May},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v238/hood24a/hood24a.pdf},
  url = 	 {https://proceedings.mlr.press/v238/hood24a.html},
  abstract = 	 {This paper introduces AL$\ell_0$CORE, a new form of probabilistic non-negative tensor decomposition. AL$\ell_0$CORE is a Tucker decomposition that constrains the number of non-zero elements (i.e., the $\ell_0$-norm) of the core tensor to be at most $Q$. While the user dictates the total budget $Q$, the locations and values of the non-zero elements are latent variables allocated across the core tensor during inference. AL$\ell_0$CORE—i.e., allocated $\ell_0$-constrained core—thus enjoys both the computational tractability of canonical polyadic (CP) decomposition and the qualitatively appealing latent structure of Tucker. In a suite of real-data experiments, we demonstrate that AL$\ell_0$CORE typically requires only tiny fractions (e.g., 1%) of the core to achieve the same results as Tucker at a correspondingly small fraction of the cost.}
}