论文标题
与数据有关的修剪以找到获胜的彩票
Data-dependent Pruning to find the Winning Lottery Ticket
论文作者
论文摘要
彩票票证假设假设新鲜初始化的神经网络包含一个小的子网，可以隔离训练，以实现与完整网络相似的性能。我们的论文研究了几种搜索此类子网的替代方法。我们得出的结论是，以训练损失的梯度形式（如SIP方法所做的那样）将依赖性组件纳入修剪标准中，始终提高现有的修剪算法的性能。
The Lottery Ticket Hypothesis postulates that a freshly initialized neural network contains a small subnetwork that can be trained in isolation to achieve similar performance as the full network. Our paper examines several alternatives to search for such subnetworks. We conclude that incorporating a data dependent component into the pruning criterion in the form of the gradient of the training loss -- as done in the SNIP method -- consistently improves the performance of existing pruning algorithms.
