We propose a novel prediction interval method to learn prediction mean values, lower and upper bounds of prediction intervals from three independently trained neural networks only using the standard mean squared error (MSE) loss, for uncertainty quantification in regression tasks. Our method requires no distributional assumption on data, does not introduce unusual hyperparameters to either the neural network models or the loss function. Moreover, our method can effectively identify out-of-distribution samples and reasonably quantify their uncertainty. Numerical experiments on benchmark regression problems show that our method outperforms the state-of-the-art methods with respect to predictive uncertainty quality, robustness, and identification of out-of-distribution samples.
翻译:我们提出了一个新的预测间隔方法,从三个独立训练的神经网络中学习预测平均值、预测间隔的下限和上限,仅使用标准平均正方差损失,用于回归任务中的不确定性量化。我们的方法不要求对数据进行分配假设,不向神经网络模型或损失函数引入异常的超参数。此外,我们的方法可以有效地识别分布范围之外的样本,并合理地量化其不确定性。基准回归问题的数值实验表明,我们的方法在预测不确定性质量、稳健性和确定分配以外的样本方面超过了最先进的方法。