The Randomness of Input Data Spaces is an A Priori Predictor for Generalization
KI 2022: Advances in Artificial Intelligence(2022)
摘要
Over-parameterized models can perfectly learn various types of data distributions, however, generalization error is usually lower for real data in comparison to artificial data. This suggests that the properties of data distributions have an impact on generalization capability. This work focuses on the search space defined by the input data and assumes that the correlation between labels of neighboring input values influences generalization. If correlation is low, the randomness of the input data space is high leading to high generalization error. We suggest to measure the randomness of an input data space using Maurer’s universal. Results for synthetic classification tasks and common image classification benchmarks (MNIST, CIFAR10, and Microsoft’s cats vs. dogs data set) find a high correlation between the randomness of input data spaces and the generalization error of deep neural networks for binary classification problems.
更多查看译文
关键词
Deep learning, Label landscape, Generalization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要