Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon

TL;DR

This paper introduces a layer-wise pruning method for deep neural networks that uses second-order derivatives to prune parameters independently, ensuring minimal performance loss and requiring only light retraining.

Contribution

It proposes a novel layer-wise pruning approach based on second-order derivatives with theoretical performance guarantees and minimal retraining needs.

Findings

Effective compression of deep networks demonstrated on benchmark datasets.

Performance drop is bounded and recoverable with light retraining.

Outperforms several state-of-the-art pruning methods.

Abstract

How to develop slim and accurate deep neural networks has become crucial for real- world applications, especially for those employed in embedded systems. Though previous work along this research line has shown some promising results, most existing methods either fail to significantly compress a well-trained deep network or require a heavy retraining process for the pruned deep network to re-boost its prediction performance. In this paper, we propose a new layer-wise pruning method for deep neural networks. In our proposed method, parameters of each individual layer are pruned independently based on second order derivatives of a layer-wise error function with respect to the corresponding parameters. We prove that the final prediction performance drop after pruning is bounded by a linear combination of the reconstructed errors caused at each layer. Therefore, there is a guarantee that one only needs to perform a light retraining process on the pruned network to resume its original prediction performance. We conduct extensive experiments on benchmark datasets to demonstrate the effectiveness of our pruning method compared with several state-of-the-art baseline methods.