论文标题
深度证据回归的不合理效力
The Unreasonable Effectiveness of Deep Evidential Regression
论文作者
论文摘要
由于机器学习系统越来越多地部署在安全 - 关键领域，因此在机器学习系统中有很大的不确定性推理。一种基于不确定性感知回归的神经网络（NNS）的新方法，基于学习的证据分布和认识性不确定性，对传统的确定性方法和典型的贝叶斯NNS有希望，特别是具有解散质量和认知不确定性的能力。尽管深度证据回归（DER）有一些经验的成功，但数学基础中仍然存在重要的差距，这些差距提出了一个问题，即为什么提出的技术似乎有效。我们详细介绍了理论上的缺点，并分析了合成和现实世界数据集的性能，表明深证回归是一种启发式，而不是确切的不确定性量化。我们继续讨论如何从NNS中提取质地和认知不确定性的更正和重新定义。
There is a significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware regression-based neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, notably with the capabilities to disentangle aleatoric and epistemic uncertainties. Despite some empirical success of Deep Evidential Regression (DER), there are important gaps in the mathematical foundation that raise the question of why the proposed technique seemingly works. We detail the theoretical shortcomings and analyze the performance on synthetic and real-world data sets, showing that Deep Evidential Regression is a heuristic rather than an exact uncertainty quantification. We go on to discuss corrections and redefinitions of how aleatoric and epistemic uncertainties should be extracted from NNs.
