Raw outputs for Simulation Study 1: Number of Trials

The folders contain all the raw output of the first simulation study from the paper:<br>"Generalization in neural posterior estimation: Case studies with the racing diffusion model".<br><br>The structure of the folder is as follows:<br>- `experiment_1`: Study folder<br> - `rdm_*`: Study condition folder (e.g., rdm_simple refers to the default settings)<br> - `flow_matching`: Output related to neural posterior estimation (NPE)<br> - `checkpoints`: Includes a `model.keras` file that contains the checkpoint of the NPE<br> for this condition<br> - `metrics`: Aggregated metrics based on posterior samples from NPE and MCMC<br> - `npe_samples`: Raw posterior samples from NPE<br> - `mcmc_samples`: Raw posterior samples obtained from Markov chain Monte Carlo (MCMC)<br> - `test_data`: Test datasets<br><br>The names of the study conditions are as follows:<br><br>- `experiment_1`:<br> - `rdm_simple`: Default settings with trial number training range {250, 500, 750, 1000}<br> - `rdm_simple_discrete_lower`: Default settings with trial number training range [50, ..., 250]<br> - `rdm_simple_discrete_upper`: Default settings with trial number training range [1000, ..., 1200]<br> - `rdm_simple_discrete_lower`: Default settings with trial number training range [50, ..., 1200]<br>All datasets and posterior samples are stored in HDF5 files. Aggregated statistics are stored in CSV format.<br>