TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
This work addresses the problem of efficient and flexible time series prediction for applications like forecasting and interpolation, representing an incremental improvement over prior methods.
The authors tackled multivariate probabilistic time series prediction by proposing TACTiS-2, a model that simplifies attentional copulas to scale linearly with variables instead of factorially, achieving state-of-the-art performance in forecasting tasks.
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.