Economy Statistical Recurrent Units For Inferring Nonlinear Granger Causality
Authors: Saurabh Khanna, Vincent Y. F. Tan
ICLR 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments are carried out to demonstrate that the proposed economy-SRU based time series prediction model outperforms the MLP, LSTM and attention-gated CNN-based time series models considered previously for inferring Granger causality. |
| Researcher Affiliation | Academia | Saurabh Khanna Department of Electrical and Computer Engineering National University of Singapore elesaur@nus.edu.sg Vincent Y. F. Tan Department of Electrical and Computer Engineering Department of Mathematics National University of Singapore vtan@nus.edu.sg |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Pytorch implementations of the proposed componentwise SRU and e SRU models are shared at https://github.com/sakhanna/SRU_for_GCI. |
| Open Datasets | Yes | For the BOLD signals: 'we use simulated BOLD time series measurements corresponding to the five different human subjects (labelled as 2 to 6) in the Sim-3.mat file shared at https://www.fmrib.ox.ac.uk/datasets/netsim/index.html.' For DREAM-3: 'DREAM-3 In Silico Network Inference Challenge (Prill et al. (2010); Marbach et al. (2009))'. |
| Dataset Splits | Yes | Two-fold crossvalidation across [5e-5, 1e-1] |
| Hardware Specification | No | The paper does not explicitly describe the hardware used to run its experiments. |
| Software Dependencies | No | The paper mentions 'Pytorch implementation' for the models but does not provide specific version numbers for Pytorch or other software dependencies. |
| Experiment Setup | Yes | Tables 7 to 11 summarize the chosen hyperparameters and configurations of the different NN/RNN models used for generating the results reported in Section 5. |