Neural Spatio-Temporal Point Processes

Abstract

We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and space. Central to our approach is a combination of continuous-time neural networks with two novel neural architectures, \ie, Jump and Attentive Continuous-time Normalizing Flows. This approach allows us to learn complex distributions for both the spatial and temporal domain and to condition non-trivially on the observed event history. We validate our models on data sets from a wide variety of contexts such as seismology, epidemiology, urban mobility, and neuroscience.

Cite

Text

Chen et al. "Neural Spatio-Temporal Point Processes." International Conference on Learning Representations, 2021.

Markdown

[Chen et al. "Neural Spatio-Temporal Point Processes." International Conference on Learning Representations, 2021.](https://mlanthology.org/iclr/2021/chen2021iclr-neural/)

BibTeX

@inproceedings{chen2021iclr-neural,
  title     = {{Neural Spatio-Temporal Point Processes}},
  author    = {Chen, Ricky T. Q. and Amos, Brandon and Nickel, Maximilian},
  booktitle = {International Conference on Learning Representations},
  year      = {2021},
  url       = {https://mlanthology.org/iclr/2021/chen2021iclr-neural/}
}