no code implementations • 14 Mar 2022 • Luca Grementieri, Paolo Galeone
We propose neural sparse linear solvers, a deep learning framework to learn approximate solvers for sparse symmetric linear systems.
no code implementations • 14 Jan 2022 • Luca Grementieri, Francesco Finelli
To the best of our knowledge, this is the largest dataset for static analysis problems and it is the first public dataset of sparse linear systems (containing both the matrix and a realistic constant term).
no code implementations • 26 Apr 2021 • Luca Grementieri, Rita Fioresi
We discover that deep ReLU neural network classifiers can see a low-dimensional Riemannian manifold structure on data.