The estimation of time-varying quantities is a fundamental component of decision making in fields such as healthcare and finance. However, the practical utility of such estimates is limited by how accurately they quantify predictive uncertainty. In this work, we address the problem of estimating the joint predictive distribution of high-dimensional multivariate time series. We propose a versatile method, based on the transformer architecture, that estimates joint distributions using an attention-based decoder that provably learns to mimic the properties of non-parametric copulas. The resulting model has several desirable properties: it can scale to hundreds of time series, supports both forecasting and interpolation, can handle unaligned and non-uniformly sampled data, and can seamlessly adapt to missing data during training. We demonstrate these properties empirically and show that our model produces state-of-the-art predictions on several real-world datasets.

翻译：时间分配数量估算是医疗保健和金融等领域决策的一个基本组成部分。然而,这种估算的实际用途受到如何准确量化预测不确定性的限制。在这项工作中,我们解决了估算高维多变时间序列联合预测分布的问题。我们根据变压器结构提出了一个多种方法,即利用基于注意的解码器估算联合分布,该解码器可以明显地学习模拟非参数相交点的特性。由此形成的模型具有若干可取的特性:它可以缩到数百个时间序列,支持预测和内推,能够处理不匹配和非统一抽样的数据,并且能够在培训期间顺利地适应缺失的数据。我们用实验方式展示了这些特性,并表明我们的模型在几个真实世界数据集上产生了最新的预测。