ESPN：极度稀疏的修剪网络
ESPN: Extremely Sparse Pruned Networks
摘要：
深度神经网络通常是高度过度参数化的，禁止它们在计算有限的系统中使用。然而，最近的一系列工作表明，通过在训练之前识别与重要权重相对应的神经元指示符（或掩码）的子集，可以大大减少深度网络的大小。我们证明了一个简单的迭代掩码发现方法可以实现非常深的网络的最先进的压缩。我们的算法代表了Single Shot网络修剪方法（如SNIP）与彩票类型方法之间的混合方法。我们在几个数据集上验证了我们的方法，并在测试精度和压缩比方面优于几种现有的剪枝方法。
英文摘要：
Deep neural networks are often highly overparameterized, prohibiting their use in compute-limited systems. However, a line of recent works has shown that the size of deep networks can be considerably reduced by identifying a subset of neuron indicators (or mask) that correspond to significant weights prior to training. We demonstrate that an simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks. Our algorithm represents a hybrid approach between single shot network pruning methods (such as SNIP) with Lottery-Ticket type approaches. We validate our approach on several datasets and outperform several existing pruning approaches in both test accuracy and compression ratio.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
