论文标题
通过傅立叶分析赢得彩票：频率指导网络修剪
Win the Lottery Ticket via Fourier Analysis: Frequencies Guided Network Pruning
论文作者
论文摘要
由于最近深度学习取得了显着的成功，因此迫切需要有效的网络压缩算法来释放边缘设备的潜在计算能力，例如智能手机或平板电脑。但是，最佳的网络修剪是一项非平凡的任务，在数学上是NP困难的问题。以前的研究人员解释说，培训修剪的网络购买彩票。在本文中，我们研究了基于幅度的修剪（MBP）方案，并通过对深度学习模型的傅立叶分析从新的角度进行分析，以指导模型名称。除了使用傅立叶变换解释MBP的概括能力外，我们还提出了一种新型的两阶段修剪方法，其中一个阶段是获得修剪的网络的拓扑结构，另一个阶段是重新训练修剪的网络，以使用从频率域上的下部到更高的知识蒸馏来恢复能力。与其他传统的MBP算法相比，对CIFAR-10和CIFAR-100的广泛实验证明了我们基于傅立叶分析的新型MBP的优势。
With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge devices, such as smartphones or tablets. However, optimal network pruning is a non-trivial task which mathematically is an NP-hard problem. Previous researchers explain training a pruned network as buying a lottery ticket. In this paper, we investigate the Magnitude-Based Pruning (MBP) scheme and analyze it from a novel perspective through Fourier analysis on the deep learning model to guide model designation. Besides explaining the generalization ability of MBP using Fourier transform, we also propose a novel two-stage pruning approach, where one stage is to obtain the topological structure of the pruned network and the other stage is to retrain the pruned network to recover the capacity using knowledge distillation from lower to higher on the frequency domain. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate the superiority of our novel Fourier analysis based MBP compared to other traditional MBP algorithms.
