[1710.05468] Generalization in Deep Learning

BRANK

Statistics > Machine LearningTitle: Generalization in Deep Learning(Submitted on 16 Oct 2017)Abstract: This paper explains why deep learning can generalize well, despite large capacity and possible algorithmic instability, nonrobustness, and sharp minima, effectively addressing an open problem in the literature. Based on our theoretical insight, this paper also proposes a family of new regularization methods. Its simplest member was empirically shown to improve base models and achieve state-of-the-art performance on MNIST and CIFAR-10 benchmarks. Moreover, this paper presents both data-dependent and data-independent generalization guarantees with improved convergence rates. Our results suggest several new open areas of research.From: Kenji Kawaguchi [view email][v1]Mon, 16 Oct 2017 02:21:24 GMT (659kb)