Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations
Official code for the paper:
Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations
Anand Jerry George and Nicolas Macris
Accepted to AISTATS, 2025
This repository contains the code implementation of the methods and experiments presented in our paper. The goal of this work is to approach the sampling problem using Stochastic interpolants framework.
The python packages required to run this code can be found in requirements.txt. The main code files can be found in the folder stint_sampler.
Run the main.py script for training the model.
Hyperparameters used in the implementation can be found in the configs directory.
The script make_plots.py can be used to generate the figures in the paper.
If you find this code useful, please consider citing our paper.
This project is licensed under the MIT License - see the LICENSE file for details.