Search Results for author: Paul Eibensteiner

Found 1 papers, 0 papers with code

Gradient-based Weight Density Balancing for Robust Dynamic Sparse Training

no code implementations25 Oct 2022 Mathias Parger, Alexander Ertl, Paul Eibensteiner, Joerg H. Mueller, Martin Winter, Markus Steinberger

Typically, the weights are redistributed after a predefined number of weight updates, removing a fraction of the parameters of each layer and inserting them at different locations in the same layers.

Cannot find the paper you are looking for? You can Submit a new open access paper.