GRU-ODE-Bayes: Continuous Modeling of Sporadically-Observed Time Series

Authors: Edward De Brouwer, Jaak Simm, Adam Arany, Yves Moreau

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Additionally, empirical evaluation shows that our method outperforms the state of the art on both synthetic data and real-world data with applications in healthcare and climate forecast.
Researcher Affiliation Academia Edward De Brouwer ESAT-STADIUS KU LEUVEN Leuven, 3001, Belgium edward.debrouwer@esat.kuleuven.be
Pseudocode Yes Algorithm 1 GRU-ODE-Bayes
Open Source Code Yes Code is available in the following anonymous repository : https://github.com/edebrouwer/gru_ ode_bayes
Open Datasets Yes We use the publicly available MIMIC-III clinical database (Johnson et al., 2016)... We use the publicly available United State Historical Climatology Network (USHCN) daily data set (Menne et al.)
Dataset Splits Yes We report the performance using 5-fold cross-validation. Hyperparameters (dropout and weight decay) are chosen using an inner holdout validation set (20%) and performance are assessed on a left-out test set (10%).
Hardware Specification Yes We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research.
Software Dependencies No The paper does not provide specific version numbers for software dependencies (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes Hyperparameters (dropout and weight decay) are chosen using an inner holdout validation set (20%) and performance are assessed on a left-out test set (10%). Those folds are reused for each model we evaluated for sake of reproducibility and fair comparison (More details in Appendix O).