https://github.com/zib-iol/cgavi
Code for the paper: Wirth, E.S. and Pokutta, S., 2022, May. Conditional gradients for the approximately vanishing ideal. In International Conference on Artificial Intelligence and Statistics (pp. 2191-2209). PMLR.
https://github.com/zib-iol/cgavi
frank-wolfe frank-wolfe-method vanishing-ideal
Last synced: 6 months ago
JSON representation
Code for the paper: Wirth, E.S. and Pokutta, S., 2022, May. Conditional gradients for the approximately vanishing ideal. In International Conference on Artificial Intelligence and Statistics (pp. 2191-2209). PMLR.
- Host: GitHub
- URL: https://github.com/zib-iol/cgavi
- Owner: ZIB-IOL
- License: mit
- Created: 2022-01-31T14:52:45.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2023-08-24T13:27:50.000Z (about 2 years ago)
- Last Synced: 2025-02-07T01:32:09.078Z (8 months ago)
- Topics: frank-wolfe, frank-wolfe-method, vanishing-ideal
- Language: Python
- Homepage:
- Size: 17.2 MB
- Stars: 3
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Citation: CITATIONS.bib
Awesome Lists containing this project
README
# Conditional Gradients for the Approximate Vanishing Ideal
Code for the paper:
[Wirth, E. S., & Pokutta, S. (2022, May). Conditional gradients for the approximately vanishing ideal.
In Proceedings of the International Conference on Artificial Intelligence and Statistics (pp. 2191-2209).
PMLR.](https://proceedings.mlr.press/v151/wirth22a.html)
and
[Wirth, E. and Pokutta, S., 2022. Conditional Gradients for the Approximate Vanishing Ideal.
arXiv preprint arXiv:2202.03349.](https://arxiv.org/abs/2202.03349)
## References
This project is an extension of the previously published release and Git repository
[cgavi](https://github.com/ZIB-IOL/cgavi/releases/tag/v1.0.0) and
[avi_at_scale](https://github.com/ZIB-IOL/avi_at_scale),
respectively.
## Installation guide
Download the repository and store it in your preferred location, say ~/tmp.
Open your terminal and navigate to ~/tmp.
Run the command:
```shell script
$ conda env create --file environment.yml
```
This will create the conda environment cgavi.
Activate the conda environment with:
```shell script
$ conda activate cgavi
```
Run the tests:
```python3 script
>>> python3 -m unittest
```
No errors should occur.
Execute the experiments:
```python3 script
>>> python3 experiments_cgavi.py
```
This will create folders named data_frames and plots, which contain subfolders containing the experiment results and
the plots, respectively.
The performance experiments can be displayed as latex_code by executing:
```python3 script
>>> experiments_to_latex_cgavi.py
```