The ALL0CORE Tensor Decomposition for Sparse Count Data

arXiv:2403.06153v1 Announce Type: cross
Abstract: This paper introduces ALL0CORE, a new form of probabilistic non-negative tensor decomposition. ALL0CORE is a Tucker decomposition where the number of non-zero elements (i.e., the L0-norm) of the core tensor is constrained to a preset value Q much smaller than the size of the core. While the user dictates the total budget Q, the locations and values of the non-zero elements are latent variables and allocated across the core tensor during inference. ALL0CORE -- i.e., …

abstract arxiv core count cs.lg data form negative norm paper stat.ml tensor tucker type value