4 citations · 7 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2020★ 2 cited
RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow
Samuel Glass, Simeon Spasov, Pietro Liò
A novel method to identify salient computational paths within randomly wired neural networks before training is proposed. The computational graph is pruned based on a node mass pro…
cs.LG2019★ 4 cited
Dynamic Neural Network Channel Execution for Efficient Training
Simeon E. Spasov, Pietro Lio
Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving…