https://github.com/divelab/rmwggis
Official implementation of "Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models" [ICLR2023]
https://github.com/divelab/rmwggis
Last synced: about 1 year ago
JSON representation
Official implementation of "Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models" [ICLR2023]
- Host: GitHub
- URL: https://github.com/divelab/rmwggis
- Owner: divelab
- Created: 2022-10-09T23:26:08.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-01-31T20:40:48.000Z (over 3 years ago)
- Last Synced: 2025-04-05T02:21:43.253Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 2.87 MB
- Stars: 9
- Watchers: 0
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models
This is the official implementation of the **RMwGGIS** method proposed in the following paper.
Meng Liu, Haoran Liu, and Shuiwang Ji. "[Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models](https://openreview.net/forum?id=9DZKk85Z4zA)". [ICLR 2023]
Visualization of learned energy functions on 32-dimensional synthetic discrete datasets.
There is [an implementation from the community](https://github.com/J-zin/RMwGGIS) as well.
## Requirements
We include key dependencies below.
* PyTorch
* tqdm
* sympy
* distutils
## Run
To run the experiments on synthetic discrete data, please refer to the commands in [`run.sh`](https://github.com/divelab/RMwGGIS/blob/main/RMwGGIS/run.sh).
## Reference
```
@inproceedings{liu2023rmwggis,
title={Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models},
author={Liu, Meng and Liu, Haoran and Ji, Shuiwang},
booktitle={International Conference on Learning Representations},
year={2023}
}
```