convexfi / spectralGraphTopology

Structured Graph Learning via Laplacian Spectral Constraints (NeurIPS 2019)
https://CRAN.R-project.org/package=spectralGraphTopology
GNU General Public License v3.0
59 stars 17 forks source link

explore the sparse structure of the vector w #5

Closed mirca closed 5 years ago

mirca commented 5 years ago

The vector w is very sparse specially when the number of components of the graph is large. I should look into exploring this fact and use more efficient data structures probably from the Matrix package.

mirca commented 5 years ago

More precisely, change the L operator to act on sparse vectors.