论文标题
使用alpha-Diverence的贝叶斯神经网络的可靠不确定性
Reliable Uncertainties for Bayesian Neural Networks using Alpha-divergences
论文作者
论文摘要
贝叶斯神经网络（BNN）经常在训练后未校准，通常会倾向于过度自信。因此，在计算复杂性方面，设计有效影响的有效校准方法是核心利益。在本文中，我们介绍了基于信息几何形状的α分歧的BNN的校准方法。我们比较了α差异在训练和校准中的使用，并展示了在校准中的使用如何为Alpha的特定选择提供更好的校准不确定性估计，并且对于复杂的网络架构而言更有效。我们从经验上证明了α校准在涉及参数估计和输出不确定性之间的相关性的回归问题中的优势。
Bayesian Neural Networks (BNNs) often result uncalibrated after training, usually tending towards overconfidence. Devising effective calibration methods with low impact in terms of computational complexity is thus of central interest. In this paper we present calibration methods for BNNs based on the alpha divergences from Information Geometry. We compare the use of alpha divergence in training and in calibration, and we show how the use in calibration provides better calibrated uncertainty estimates for specific choices of alpha and is more efficient especially for complex network architectures. We empirically demonstrate the advantages of alpha calibration in regression problems involving parameter estimation and inferred correlations between output uncertainties.
