Machine Learning

Generalization in Deep Learning

Tagged: , , ,

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 1 year, 5 months ago.


  • arXiv
    5 pts

    Generalization in Deep Learning

    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.

    Generalization in Deep Learning
    by Kenji Kawaguchi, Leslie Pack Kaelbling, Yoshua Bengio
    https://arxiv.org/pdf/1710.05468v1.pdf

You must be logged in to reply to this topic.