Exploring Structural Sparsity of Deep Networks Via Inverse Scale Spaces
Exploring Structural Sparsity of Deep Networks Via Inverse Scale Spaces
The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. On the other hand, training neural networks without over-parameterization faces …