arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2005.00178cs.LGstat.ML
收藏

论神经网络中不变性的好处

On the Benefits of Invariance in Neural Networks

University of Oxford(牛津大学);Imperial College London(伦敦帝国学院);University of British Columbia(不列颠哥伦比亚大学)

Clare Lyle, Mark van der Wilk, Marta Kwiatkowska, Yarin Gal, Benjamin Bloem-Reddy

摘要:

许多现实世界的数据分析问题都表现出不变结构,利用这种结构的模型表现出令人印象深刻的经验性能,特别是在深度学习中。虽然文献中包含了各种将不变性纳入模型的方法,但理论上的理解很差,并且没有办法评估何时应该首选一种方法。在这项工作中,我们分析了深度学习中存在不变性的两种广泛使用的方法的优点和局限性:数据增强和特征平均。我们证明了使用数据增强进行训练可以更好地估计风险及其梯度,并且我们为使用数据增强训练的模型提供了PAC-Bayes泛化界。我们还表明,相比数据增强,特征平均减少了泛化误差时,使用凸损失,并收紧PAC贝叶斯界限。我们提供了这些理论结果的实证支持,包括为什么泛化可能无法通过数据增强训练来改善的演示:“学习不变性”在训练分布之外失败。

英文摘要:

Many real world data analysis problems exhibit invariant structure, and models that take advantage of this structure have shown impressive empirical performance, particularly in deep learning. While the literature contains a variety of methods to incorporate invariance into models, theoretical understanding is poor and there is no way to assess when one method should be preferred over another. In this work, we analyze the benefits and limitations of two widely used approaches in deep learning in the presence of invariance: data augmentation and feature averaging. We prove that training with data augmentation leads to better estimates of risk and gradients thereof, and we provide a PAC-Bayes generalization bound for models trained with data augmentation. We also show that compared to data augmentation, feature averaging reduces generalization error when used with convex losses, and tightens PAC-Bayes bounds. We provide empirical support of these theoretical results, including a demonstration of why generalization may not improve by training with data augmentation: the `learned invariance' fails outside of the training distribution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑