Stage 1 of P-ROCKET employs group-wise regularization similarly to our initial ADMM-based Algorithm, but introduces dynamically varying penalties to greatly accelerate the process.
Filter pruning has attracted increasing attention in recent years for its capacity in compressing and accelerating convolutional neural networks.
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs). Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs.
To overcome this problem, we propose to compress CNNs and alleviate performance degradation via joint matrix decomposition, which is different from existing works that compressed layers separately.