论文标题
深度不确定：比较深度学习算法中不确定性定量的方法
Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
论文作者
论文摘要
我们介绍了在简单的物理系统中深度学习算法中不确定性定量（UQ）方法的比较。将三种最常见的不确定性定量方法 - 贝叶斯神经网络（BNN），混凝土辍学（CD）和深层集合（DE） - 与标准的分析误差传播进行了比较。我们以机器学习（“认识论”和“ Aleatoric”）和物理科学（“统计”和“系统的”）的特征术语讨论了这种比较。比较是根据单个摆的模拟实验测量来进行的，这是一种用于研究测量和分析技术的典型物理系统。我们的结果突出了使用这些UQ方法时可能发生的一些陷阱。例如，当训练集中的噪声变化很小时，所有方法都独立于输入预测相同的相对不确定性。在BNN中，这个问题尤其难以避免。另一方面，当测试集包含远离训练分布的样本时，我们发现没有任何方法足以增加与其预测相关的不确定性。对于CD来说，这个问题特别明显。鉴于这些结果，我们就UQ方法的使用和解释提出了一些建议。
We present a comparison of methods for uncertainty quantification (UQ) in deep learning algorithms in the context of a simple physical system. Three of the most common uncertainty quantification methods - Bayesian Neural Networks (BNN), Concrete Dropout (CD), and Deep Ensembles (DE) - are compared to the standard analytic error propagation. We discuss this comparison in terms endemic to both machine learning ("epistemic" and "aleatoric") and the physical sciences ("statistical" and "systematic"). The comparisons are presented in terms of simulated experimental measurements of a single pendulum - a prototypical physical system for studying measurement and analysis techniques. Our results highlight some pitfalls that may occur when using these UQ methods. For example, when the variation of noise in the training set is small, all methods predicted the same relative uncertainty independently of the inputs. This issue is particularly hard to avoid in BNN. On the other hand, when the test set contains samples far from the training distribution, we found that no methods sufficiently increased the uncertainties associated to their predictions. This problem was particularly clear for CD. In light of these results, we make some recommendations for usage and interpretation of UQ methods.
