arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.08324cs.LGcs.AI
收藏

通过稳定分布传播进行不确定性量化

Uncertainty Quantification via Stable Distribution Propagation

University of Salzburg(萨尔茨堡大学);University of Konstanz(康斯坦茨大学);Stanford University(斯坦福大学);University of Bonn(波恩大学);MIT-IBM Watson AI Lab(麻省理工学院-IBM沃森人工智能实验室)

Felix Petersen, Aashwin Mishra, Hilde Kuehne, Christian Borgelt, Oliver Deussen, Mikhail Yurochkin

AI总结:

提出基于局部线性化的稳定概率分布传播方法,在总变差距离下对ReLU非线性最优,可量化神经网络输出不确定性,在置信区间预测和分布外选择性预测中优于矩匹配等方法。

摘要:

我们提出了一种通过神经网络传播稳定概率分布的新方法。该方法基于局部线性化,我们证明对于ReLU非线性,这是在总变差距离意义下的最优近似。这使得能够将高斯和柯西输入不确定性通过神经网络进行传播,从而量化其输出不确定性。为展示分布传播的实用性,我们将该方法应用于预测校准的置信区间以及分布外数据的选择性预测。结果证明了分布传播的广泛适用性,并展示了该方法相较于矩匹配等其他方法的优势。

英文摘要:

We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal approximation in terms of total variation distance for the ReLU non-linearity. This allows propagating Gaussian and Cauchy input uncertainties through neural networks to quantify their output uncertainties. To demonstrate the utility of propagating distributions, we apply the proposed method to predicting calibrated confidence intervals and selective prediction on out-of-distribution data. The results demonstrate a broad applicability of propagating distributions and show the advantages of our method over other approaches such as moment matching.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑