arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.04742cs.LGcs.AIstat.ML
收藏

使用贝叶斯深度学习量化离散-连续和倾斜数据中的不确定性

Quantifying Uncertainty in Discrete-Continuous and Skewed Data with Bayesian Deep Learning

Northeastern University(东北大学);risQ Inc.(risQ公司);Bay Area Environmental Research Institute(湾区环境研究所);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心);NASA Advanced Supercomputing Division(美国国家航空航天局高级超级计算部)

Thomas Vandal, Evan Kodra, Jennifer Dy, Sangram Ganguly, Ramakrishna Nemani, Auroop R. Ganguly

摘要:

深度学习(DL)方法一直在改变计算机视觉,并对包括气候变化在内的其他领域进行创新性调整。对于深度学习,以普及科学和工程(S&E)的应用程序,风险管理是一个核心组成部分,良好的特征化的不确定性估计必须伴随着预测。然而,S&E观测和模型模拟通常遵循严重偏斜的分布,并且不能用DL方法很好地建模,因为它们通常优化高斯或欧几里得似然损失。贝叶斯深度学习(BDL)的最新发展为我们提供了一个基础,它试图从随机的噪声观测和未知的模型参数中捕获不确定性。在这里,我们提出了一个离散连续的BDL模型与高斯和对数正态似然不确定性量化(UQ)。我们通过在“DeepSD”上开发UQ估计来证明这种方法,DeepSD是一种基于超分辨率的DL模型,用于气候中应用于降水的统计降尺度(SD),它遵循一个非常偏斜的分布。我们发现,离散-连续模型在预测精度和不确定性校准方面优于基本高斯分布。此外,我们发现,对数正态分布,它可以处理偏态分布,在极端情况下产生质量不确定性估计。这些结果可能对整个S&E以及其他领域(如金融和经济)都很重要,在这些领域,极端情况往往具有重大意义。此外,据我们所知,这是第一个UQ模型在SD的任意和认知的不确定性的特点。

英文摘要:

Deep Learning (DL) methods have been transforming computer vision with innovative adaptations to other domains including climate change. For DL to pervade Science and Engineering (S&E) applications where risk management is a core component, well-characterized uncertainty estimates must accompany predictions. However, S&E observations and model-simulations often follow heavily skewed distributions and are not well modeled with DL approaches, since they usually optimize a Gaussian, or Euclidean, likelihood loss. Recent developments in Bayesian Deep Learning (BDL), which attempts to capture uncertainties from noisy observations, aleatoric, and from unknown model parameters, epistemic, provide us a foundation. Here we present a discrete-continuous BDL model with Gaussian and lognormal likelihoods for uncertainty quantification (UQ). We demonstrate the approach by developing UQ estimates on `DeepSD', a super-resolution based DL model for Statistical Downscaling (SD) in climate applied to precipitation, which follows an extremely skewed distribution. We find that the discrete-continuous models outperform a basic Gaussian distribution in terms of predictive accuracy and uncertainty calibration. Furthermore, we find that the lognormal distribution, which can handle skewed distributions, produces quality uncertainty estimates at the extremes. Such results may be important across S&E, as well as other domains such as finance and economics, where extremes are often of significant interest. Furthermore, to our knowledge, this is the first UQ model in SD where both aleatoric and epistemic uncertainties are characterized.

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。

↑