ebflow

[NeurIPS 2023] Training Energy-Based Normalizing Flow with Score-Matching Objectives

https://github.com/chen-hao-chao/ebflow

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (11.5%) to scientific vocabulary

Keywords

density-estimation ebflow energy-based-model flow-based-model normalizing-flows pytorch score-matching

Last synced: 6 months ago · JSON representation ·

Repository

[NeurIPS 2023] Training Energy-Based Normalizing Flow with Score-Matching Objectives

Basic Info

Host: GitHub
Owner: chen-hao-chao
Language: Python
Default Branch: master
Homepage: https://chen-hao-chao.github.io/ebflow/
Size: 10.3 MB

Statistics

Stars: 8
Watchers: 2
Forks: 1
Open Issues: 0
Releases: 0

Topics

density-estimation ebflow energy-based-model flow-based-model normalizing-flows pytorch score-matching

Created over 2 years ago · Last pushed 9 months ago

Metadata Files

Readme Citation

Training Energy-Based Normalizing Flow with Score-Matching Objectives

This repository contains the code implementation of the experiments presented in the paper Training Energy-Based Normalizing Flow with Score-Matching Objectives.

ebflow ebflow

The project page is available at: https://chen-hao-chao.github.io/ebflow/

Directory Structure

Use the code in ebflow/toy_examples to reproduce the results presented in Sections 5.1 and A5.
Use the code in ebflow/real_world to reproduce the results presented in Sections 5.2, 5.3, and 5.4.

Dependencies

(Optional) Launch a Docker Container

```sh

assume the current directory is the root of this repository

docker run --rm -it --gpus all --ipc=host -v$(pwd):/app nvcr.io/nvidia/pytorch:20.12-py3

inside the docker container, run:

cd /app ```

Install Dependencies

Setup the conda environment with conda_environment.yml: sh conda env create -f conda_environment.yml Launch ebflow conda environment: sh source activate conda activate ebflow

References

This code implementation is developed based on the following repositories: - taufikxu/FD-ScoreMatching (at commit 9df0789) is licensed under the MIT License. - akandykeller/SelfNormalizingFlows (at commit 9feebb3) is licensed under the MIT License. - yang-song/scoresdepytorch (at commit cb1f359) is licensed under the Apache-2.0 License. - ermongroup/slicedscorematching (at commit 880c047) is licensed under the GPL-3.0 license. - kamenbliznashki/normalizing_flows (at commit 97a73a0). - fissoreg/relative-gradient-jacobian (at commit d2e03ca).

Citing EBFlow

If you find this code useful, please consider citing our paper. bib @inproceedings{chao2023ebflow, title={{Training Energy-Based Normalizing Flow with Score-Matching Objectives}}, author={Chen-Hao Chao and Wei-Fang Sun and Yen-Chang Hsu and Zsolt Kira and Chun-Yi Lee}, year={2023}, booktitle={Proceedings of International Conference on Neural Information Processing Systems (NeurIPS)} }

Owner

Name: Lance Chao
Login: chen-hao-chao
Kind: user
Location: Taipei
Company: National Tsing Hua University

Repositories: 2
Profile: https://github.com/chen-hao-chao

NTHU CS

Citation (CITATION.bib)

@inproceedings{chao2023ebflow,
      title={{Training Energy-Based Normalizing Flow with Score-Matching Objectives}}, 
      author={Chen-Hao Chao and Wei-Fang Sun and Yen-Chang Hsu and Zsolt Kira and Chun-Yi Lee},
      year={2023},
      booktitle={Proceedings of International Conference on Neural Information Processing Systems (NeurIPS)}
}

GitHub Events

Total

Issues event: 2
Watch event: 4
Issue comment event: 1
Push event: 2
Fork event: 1

Last Year

Issues event: 2
Watch event: 4
Issue comment event: 1
Push event: 2
Fork event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 1
Total pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Total issue authors: 1
Total pull request authors: 0
Average comments per issue: 0.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 1
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 1
Pull request authors: 0
Average comments per issue: 0.0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science