We introduce a new model for multivariate probabilistic time series prediction, designed to flexibly address a range of tasks including forecasting, interpolation, and their combinations. Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS), wherein the number of distributional parameters now scales linearly with the number of variables instead of factorially. The new objective requires the introduction of a training curriculum, which goes hand-in-hand with necessary changes to the original architecture. We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks, while maintaining the flexibility of prior work, such as seamless handling of unaligned and unevenly-sampled time series. Code is made available at https://github.com/ServiceNow/TACTiS.

翻译：我们提出了一种新的多元概率时间序列预测模型，旨在灵活应对预测、插值及其组合等一系列任务。基于连接函数理论，我们为近期提出的基于Transformer的注意力连接函数（TACTiS）简化了目标函数，使得分布参数的数量从原先的阶乘级缩放变为与变量数量呈线性关系。该新目标函数需要引入训练课程，这与原始架构的必要变更相辅相成。实验表明，所得模型具有显著改善的训练动态，并在多种真实世界预测任务中达到最先进性能，同时保持了先前工作的灵活性，例如无缝处理非对齐和不均匀采样的时间序列。代码已开源在https://github.com/ServiceNow/TACTiS。