论文标题
通过矩阵草图的神经网络预测间隔的可扩展计算
Scalable computation of prediction intervals for neural networks via matrix sketching
论文作者
论文摘要
在现代神经网络的预测中考虑不确定性是许多领域的一项具有挑战性且重要的任务。现有的不确定性估计算法需要修改模型架构和培训程序（例如贝叶斯神经网络）或大大增加基于结合的方法之类的预测的计算成本。这项工作提出了一种新算法，可以应用于给定的训练有素的神经网络并产生近似的预测间隔。该方法基于统计中的经典三角洲方法，但通过使用矩阵素描来近似雅各布矩阵来实现计算效率。最终的算法具有竞争性的，该算法具有最新方法，用于在UCI存储库中构建各种回归数据集的预测间隔。
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.
