Numerous applications of machine learning involve predicting flexible probability distributions over model outputs. We propose Autoregressive Quantile Flows, a flexible class of probabilistic models over high-dimensional variables that can be used to accurately capture predictive aleatoric uncertainties. These models are instances of autoregressive flows trained using a novel objective based on proper scoring rules, which simplifies the calculation of computationally expensive determinants of Jacobians during training and supports new types of neural architectures. We demonstrate that these models can be used to parameterize predictive conditional distributions and improve the quality of probabilistic predictions on time series forecasting and object detection.
翻译:机器学习的许多应用都涉及对模型产出的灵活概率分布进行预测。我们提出了“自动递减量流”,这是针对高维变量的一种灵活的概率模型,可用于准确捕捉预测的偏移不确定性。这些模型是利用基于适当评分规则的新目标培训的自动递减流动的例子,它简化了计算计算Jacobian人计算费用昂贵的决定因素的方法,支持新型神经结构。我们证明这些模型可用于对预测性有条件分布进行参数化,并提高时间序列预测和物体探测的概率预测的质量。