论文标题
使用样本网络估算回归预测分布
Estimating Regression Predictive Distributions with Sample Networks
论文作者
论文摘要
估计深神经网络预测中的不确定性对于许多现实世界应用至关重要。建模不确定性的一种常见方法是选择一个参数分布并使用最大似然估计来适合数据。所选的参数形式可能很差适合数据生成分布，从而导致不可靠的不确定性估计。在这项工作中，我们提出了Samplenet，这是一种灵活且可扩展的体系结构，用于建模不确定性，避免在输出分布上指定参数形式。 Samplenets通过使用能量评分学习的样品来定义经验分布，并以凹凸不平的差异进行正规化。 Samplenets显示出能够很好地拟合广泛的分布，并且在大规模现实世界回归任务上的表现要优于基准。
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applications. A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation. The chosen parametric form can be a poor fit to the data-generating distribution, resulting in unreliable uncertainty estimates. In this work, we propose SampleNet, a flexible and scalable architecture for modeling uncertainty that avoids specifying a parametric form on the output distribution. SampleNets do so by defining an empirical distribution using samples that are learned with the Energy Score and regularized with the Sinkhorn Divergence. SampleNets are shown to be able to well-fit a wide range of distributions and to outperform baselines on large-scale real-world regression tasks.
