A Unified DNN Weight Pruning Framework Using Reweighted Optimization Methods
TimeTuesday, December 7th4:50pm - 5:10pm PST
Event Type
Research Manuscript
Approximate Computing for AI/ML
Virtual Programs
In-Person Only
DescriptionTo address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and generally fall into two categories, i.e., static regularization-based pruning and dynamic regularization-based pruning. However, the former method currently suffers either complex workloads or accuracy degradation, while the latter one takes a long time to tune the parameters. In this paper, we propose a unified DNN weight pruning framework with dynamically updated regularization terms. Our proposed method increases the compression rate, reduces the training time and reduces the number of hyper-parameters compared with state-of-the-art ADMM-based hard constraint method.