Reducing Computational and Statistical Complexity in Machine Learning Through Cardinality Sparsity
From MaRDI portal
Abstract: High-dimensional data has become ubiquitous across the sciences but causes computational and statistical challenges. A common approach for dealing with these challenges is sparsity. In this paper, we introduce a new concept of sparsity, called cardinality sparsity. Broadly speaking, we call a tensor sparse if it contains only a small number of unique values. We show that cardinality sparsity can improve deep learning and tensor regression both statistically and computationally. On the way, we generalize recent statistical theories in those fields.
This page was built for publication: Reducing Computational and Statistical Complexity in Machine Learning Through Cardinality Sparsity
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6426672)
