Latent ODEs for Irregularly-Sampled Time Series
Machine Learning
2019-07-10 v1 Machine Learning
Abstract
Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous-time hidden dynamics defined by ordinary differential equations (ODEs), a model we call ODE-RNNs. Furthermore, we use ODE-RNNs to replace the recognition network of the recently-proposed Latent ODE model. Both ODE-RNNs and Latent ODEs can naturally handle arbitrary time gaps between observations, and can explicitly model the probability of observation times using Poisson processes. We show experimentally that these ODE-based models outperform their RNN-based counterparts on irregularly-sampled data.
Cite
@article{arxiv.1907.03907,
title = {Latent ODEs for Irregularly-Sampled Time Series},
author = {Yulia Rubanova and Ricky T. Q. Chen and David Duvenaud},
journal= {arXiv preprint arXiv:1907.03907},
year = {2019}
}