Stein Self Repulsive Dynamics

[Neurips 2020] Code for: Stein Self-Repulsive Dynamics: Benefits From Past Samples

We propose a new Stein self-repulsive dynamics for obtaining diversified samples from intractable un-normalized distributions. Our idea is to introduce Stein variational gradient as a repulsive force to push the samples of Langevin dynamics away from the past trajectories.

Citation

@article{ye2020stein,
title={Stein self-repulsive dynamics: Benefits from past samples},
author={Ye, Mao and Ren, Tongzheng and Liu, Qiang},
journal={arXiv preprint arXiv:2002.09070},
year={2020}
}