With the rise of the popularity and usage of neural networks, trustworthy uncertainty estimation is becoming increasingly essential. One of the most prominent uncertainty estimation methods is Deep Ensembles (Lakshminarayanan et al., 2017) . A classical parametric model has uncertainty in the parameters due to the fact that the data on which the model is build is a random sample. A modern neural network has an additional uncertainty component since the optimization of the network is random. Lakshminarayanan et al. (2017) noted that Deep Ensembles do not incorporate the classical uncertainty induced by the effect of finite data. In this paper, we present a computationally cheap extension of Deep Ensembles for the regression setting, called Bootstrapped Deep Ensembles, that explicitly takes this classical effect of finite data into account using a modified version of the parametric bootstrap. We demonstrate through an experimental study that our method significantly improves upon standard Deep Ensembles

翻译：随着神经网络普及与应用的增长，可靠的置信度估计变得日益重要。最突出的不确定性估计方法之一是深度集成（Lakshminarayanan 等人，2017）。经典参数模型由于构建模型的数据为随机样本，其参数存在不确定性；而现代神经网络因网络优化具有随机性，还包含额外的不确定性成分。Lakshminarayanan 等人（2017）指出，深度集成并未纳入由有限数据效应引发的经典不确定性。本文针对回归任务，提出一种名为“自助法深度集成”的深度集成计算轻量扩展方法，该方法通过改进版参数自助法显式考虑了有限数据的经典效应。实验研究表明，我们的方法显著优于标准深度集成。