EDEN

Estimation of Distribution using ENergy-based models

Installation

We currently do not provide a PyPI package for eden, but you can install it directly from GitHub using pip:

pip install "eden @ git+https://github.com/FrancescoGentile/eden.git"

If you instead need to work on the source code, you can clone the repository and install the package in editable mode:

git clone https://github.com/FrancescoGentile/eden.git
cd eden

# make sure that the active environment has python>=3.10
pip install -e .

# if you also need to install the development dependencies
pip install -r requirements-dev.lock

Usage

At the moment, the command-line interface provides only the train command, which allows you to train a eden model using the provided configuration file. The configuration file is a YAML file that contains the configuration for the model architetcure, the parameters of the problem on which the model will be trained and the training parameters (e.g., the optimizer, the learning rate scheduler, the number of iterations, etc.). You can find an example configuration file in the configs directory.

To train a eden model, you can use the following command:

eden train /path/to/config.yaml