Arjun Ashok, Étienne Marcotte, Valentina Zantedeschi, Nicolas Chapados, Alexandre Drouin. TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series. (Accepted at ICLR 2024)
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.
You can install the TACTiS-2 model with pip:
pip install tactisAlternatively, the research version installs gluonts and pytorchts as dependencies which are required to replicate experiments from the paper:
pip install tactis[research]Note: tactis has been currently tested with Python 3.10.8.
With the research version of the code, train.py can be used to train the TACTiS-2 model for a specific dataset. The arguments in train.py can be used to specify the dataset, the training task (forecasting or interpolation), the hyperparameters of the model and a whole range of other training options.
There are notebooks in the that are useful in guiding training and evaluation pipeline setups: random_walk.ipynb demonstrates TACTiS-2 on a simple low-dimensional random walk dataset, and gluon_fred_md_forecasting.ipynb demonstrates how to train and evaluate TACTiS-2 on the FRED-MD dataset used in the paper. Note that the gluon_fred_md_forecasting.ipynb notebook requires GluonTS and PyTorchTS to be installed.
For an implementation of the original version of TACTiS, please see here.
Please use the following Bibtex entry to cite TACTiS-2.
@misc{ashok2023tactis2,
title={TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series},
author={Arjun Ashok and Étienne Marcotte and Valentina Zantedeschi and Nicolas Chapados and Alexandre Drouin},
year={2023},
eprint={2310.01327},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent