Timezone: »

 
Poster
Latent Ordinary Differential Equations for Irregularly-Sampled Time Series
Yulia Rubanova · Tian Qi Chen · David Duvenaud

Tue Dec 10 05:30 PM -- 07:30 PM (PST) @ East Exhibition Hall B + C #81
in Deep Learning -- Generative Models »

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.

Keywords: Time Series Analysis · Generative Models · Applications · Deep Learning
[ Paper]  [ Poster] 

Author Information

Yulia Rubanova (University of Toronto)
Tian Qi Chen (U of Toronto)
David Duvenaud (University of Toronto)

David Duvenaud is an assistant professor in computer science at the University of Toronto. His research focuses on continuous-time models, latent-variable models, and deep learning. His postdoc was done at Harvard University, and his Ph.D. at the University of Cambridge. David also co-founded Invenia, an energy forecasting and trading company.

More from the Same Authors