论文标题
使用噪声弹性来对深神经网络的概括进行排名
Using noise resilience for ranking generalization of deep neural networks
论文作者
论文摘要
最近的论文表明，充分过度参数化的神经网络甚至可以随机标签完全拟合。因此，了解网络对现实世界数据的概括性能背后的根本原因至关重要。在这项工作中，我们提出了几项措施，以预测培训数据及其参数的网络的概括误差。使用这些措施之一，基于网络的噪声弹性，我们在2020年Neurips的深度学习（PGDL）竞争中获得了第5个位置。
Recent papers have shown that sufficiently overparameterized neural networks can perfectly fit even random labels. Thus, it is crucial to understand the underlying reason behind the generalization performance of a network on real-world data. In this work, we propose several measures to predict the generalization error of a network given the training data and its parameters. Using one of these measures, based on noise resilience of the network, we secured 5th position in the predicting generalization in deep learning (PGDL) competition at NeurIPS 2020.
