Dropout就是指在深度学习网络的训练过程中,对于神经网络单元,按照一定的概率将其暂时从网络中丢弃。Dropout可以减轻过拟合问题。

VIP内容

Dropout是一种广泛使用的正则化技术,通常需要为许多体系结构获得最先进的技术。这项工作表明,dropout引入了两种截然不同但相互纠缠的正则化效应:由于dropout修改了预期的训练目标而产生的显式效应(在之前的工作中也研究过),以及可能令人惊讶的是,dropout训练更新中的随机性带来的另一种隐式效应。这种隐式正则化效应类似于小批量随机梯度下降中的随机度效应。我们通过控制实验把这两种效应分开。然后,我们推导出分析的简化,用模型的导数和损失来描述每个影响,对于深度神经网络。我们证明了这些简化的、解析的正则化器准确地捕获了辍学的重要方面,表明它们在实践中忠实地替代了dropout。

成为VIP会员查看完整内容
0
19

最新内容

This paper shows that dropout training in Generalized Linear Models is the minimax solution of a two-player, zero-sum game where an adversarial nature corrupts a statistician's covariates using a multiplicative nonparametric errors-in-variables model. In this game, nature's least favorable distribution is dropout noise, where nature independently deletes entries of the covariate vector with some fixed probability $\delta$. This result implies that dropout training indeed provides out-of-sample expected loss guarantees for distributions that arise from multiplicative perturbations of in-sample data. In addition to the decision-theoretic analysis, the paper makes two more contributions. First, there is a concrete recommendation on how to select the tuning parameter $\delta$ to guarantee that, as the sample size grows large, the in-sample loss after dropout training exceeds the true population loss with some pre-specified probability. Second, the paper provides a novel, parallelizable, Unbiased Multi-Level Monte Carlo algorithm to speed-up the implementation of dropout training. Our algorithm has a much smaller computational cost compared to the naive implementation of dropout, provided the number of data points is much smaller than the dimension of the covariate vector.

0
0
下载
预览

最新论文

This paper shows that dropout training in Generalized Linear Models is the minimax solution of a two-player, zero-sum game where an adversarial nature corrupts a statistician's covariates using a multiplicative nonparametric errors-in-variables model. In this game, nature's least favorable distribution is dropout noise, where nature independently deletes entries of the covariate vector with some fixed probability $\delta$. This result implies that dropout training indeed provides out-of-sample expected loss guarantees for distributions that arise from multiplicative perturbations of in-sample data. In addition to the decision-theoretic analysis, the paper makes two more contributions. First, there is a concrete recommendation on how to select the tuning parameter $\delta$ to guarantee that, as the sample size grows large, the in-sample loss after dropout training exceeds the true population loss with some pre-specified probability. Second, the paper provides a novel, parallelizable, Unbiased Multi-Level Monte Carlo algorithm to speed-up the implementation of dropout training. Our algorithm has a much smaller computational cost compared to the naive implementation of dropout, provided the number of data points is much smaller than the dimension of the covariate vector.

0
0
下载
预览
父主题
Top