(Pen-) Ultimate DNN Pruning
This addresses the efficiency bottleneck in pruning for DNN-based solutions, though it appears incremental as it builds on prior pruning methods.
The paper tackles the problem of time-consuming iterative retraining in DNN pruning by proposing a one-shot scheme based on Principal Component Analysis and neuron connection importance, achieving an optimized DNN without manual hyperparameter tuning.
DNN pruning reduces memory footprint and computational work of DNN-based solutions to improve performance and energy-efficiency. An effective pruning scheme should be able to systematically remove connections and/or neurons that are unnecessary or redundant, reducing the DNN size without any loss in accuracy. In this paper we show that prior pruning schemes require an extremely time-consuming iterative process that requires retraining the DNN many times to tune the pruning hyperparameters. We propose a DNN pruning scheme based on Principal Component Analysis and relative importance of each neuron's connection that automatically finds the optimized DNN in one shot without requiring hand-tuning of multiple parameters.