深度不确定性: 比较深度学习算法中的不确定性量化方法---用户7095611

我们在一个简单的物理系统的背景下，对深度学习算法中的不确定性量化(UQ)的方法进行了比较。 将三种最常用的不确定度量化方法——贝叶斯神经网络(BNN)、混凝土丢失(CD)和深度集成(DE)——与标准分析误差传播方法进行了比较。 我们从机器学习(“认知性”和“任意性”)和物理科学(“统计性”和“系统性”)两个方面来讨论这种比较。 给出了单摆模拟实验测量的比较，单摆是研究测量和分析技术的典型物理系统。 我们的结果强调了使用这些 UQ方法时可能出现的一些缺陷。 例如，当训练集中噪声的变化很小时，所有方法都能独立于输入预测相同的相对不确定度。 这个问题在BNN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能够充分增加与预测相关的不确定性。 这个问题对CD来说尤其明显。 根据这些结果，我们对UQ方法的使用和解释提出了一些建议。

原文题目：Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms

原文：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.

原文作者：João Caldeira

原文地址：https://arxiv.org/abs/2004.10710