标题： 通过矩阵压缩的神经网络预测区间可扩展计算 显示英文标题

标题： Scalable computation of prediction intervals for neural networks via matrix sketching

摘要： 在许多领域中，考虑现代神经网络预测中的不确定性是一项具有挑战性和重要的任务。 现有的不确定性估计算法需要修改模型架构和训练过程（例如，贝叶斯神经网络）或显著增加预测的计算成本，如基于集成的方法。 本工作提出了一种新算法，可以应用于给定的训练好的神经网络，并生成近似的预测区间。 该方法基于统计学中的经典delta方法，但通过使用矩阵抽样来近似雅可比矩阵，从而实现计算效率。 该算法在UCI存储库中的各种回归数据集上构建预测区间方面，与最先进的方法具有竞争力。 显示英文摘要

摘要： Accounting for the uncertainty in the predictions of modern neural networks is a challenging and important task in many domains. Existing algorithms for uncertainty estimation require modifying the model architecture and training procedure (e.g., Bayesian neural networks) or dramatically increase the computational cost of predictions such as approaches based on ensembling. This work proposes a new algorithm that can be applied to a given trained neural network and produces approximate prediction intervals. The method is based on the classical delta method in statistics but achieves computational efficiency by using matrix sketching to approximate the Jacobian matrix. The resulting algorithm is competitive with state-of-the-art approaches for constructing predictive intervals on various regression datasets from the UCI repository.