Learning Sparse Neural Networks via Sensitivity-Driven Regularization
This work addresses memory constraints for deploying neural networks in resource-limited applications, representing an incremental improvement over existing regularize-and-prune methods.
The paper tackles the challenge of memory limitations in deep neural networks by introducing a sensitivity-driven regularization method that sparsifies network weights, achieving up to twice the sparsity of other techniques at equal error rates.
The ever-increasing number of parameters in deep neural networks poses challenges for memory-limited applications. Regularize-and-prune methods aim at meeting these challenges by sparsifying the network weights. In this context we quantify the output sensitivity to the parameters (i.e. their relevance to the network output) and introduce a regularization term that gradually lowers the absolute value of parameters with low sensitivity. Thus, a very large fraction of the parameters approach zero and are eventually set to zero by simple thresholding. Our method surpasses most of the recent techniques both in terms of sparsity and error rates. In some cases, the method reaches twice the sparsity obtained by other techniques at equal error rates.