Deep probabilistic time series forecasting models have become an integral part of machine learning. While several powerful generative models have been proposed, we provide evidence that their associated inference models are oftentimes too limited and cause the generative model to predict mode-averaged dynamics. Modeaveraging is problematic since many real-world sequences are highly multi-modal, and their averaged dynamics are unphysical (e.g., predicted taxi trajectories might run through buildings on the street map). To better capture multi-modality, we develop variational dynamic mixtures (VDM): a new variational family to infer sequential latent variables. The VDM approximate posterior at each time step is a mixture density network, whose parameters come from propagating multiple samples through a recurrent architecture. This results in an expressive multi-modal posterior approximation. In an empirical study, we show that VDM outperforms competing approaches on highly multi-modal datasets from different domains.
翻译:深度概率时间序列预测模型已成为机器学习的一个组成部分。 虽然已经提出了几个强大的基因模型,但我们提供了证据,证明它们相关的推论模型往往过于有限,并导致基因模型预测模式平均动态。 模式波动有问题,因为许多现实世界序列是高度多模式的,其平均动态是非物理的(例如,预测的出租车轨迹可能穿过街道地图上的建筑物)。为了更好地捕捉多模式性,我们开发了变异动态混合物(VDM):一种新的变异式组合来推断相继潜伏变量。VDM每一步的近似外表象是一个混合密度网络,其参数来自通过一个经常结构传播多个样本。这导致一个显性多模式外表式近似。在一项实验研究中,我们显示VDM在不同区域高多模式数据集上比对立。