Many matrices associated with fast transforms posess a certain low-rank
...
Given a training set, a loss function, and a neural network architecture...
Multi-level methods are widely used for the solution of large-scale prob...
A major paradigm for learning image representations in a self-supervised...
We consider general approximation families encompassing ReLU neural netw...
The problem of approximating a dense matrix by a product of sparse facto...
Sparse matrix factorization is the problem of approximating a matrix Z b...
Many well-known matrices Z are associated to fast transforms correspondi...
Given a full column rank matrix A ∈R^m× n (m≥ n),
we consider a special ...
This paper is concerned with the approximation of the solution of partia...