1. Critical learning periods in deep networks;Achille
2. What is the state of neural network pruning?;Blalock
3. The lottery ticket hypothesis for pre-trained BERT networks;Chen;Neural Information Processing Systems (NeurIPS),2020
4. Sparsity winning twice: Better robust generalization from more efficient training;Chen
5. Progressive skeletonization: Trimming more fat from a network at initialization;de Jorge