Projection-Free CNN Pruning via Frank-Wolfe with Momentum: Sparser Models with Less Pretraining

Hamza ElMokhtar Shili, Natasha Patnaik, Isabelle Ruble +2

We investigate algorithmic variants of the Frank-Wolfe (FW) optimization method for pruning convolutional neural networks. This is motivated by the "Lottery Ticket Hypothesis", whi…