fw-generalized-selfconcordant
Repository for the NeurIPS2021 paper "Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions"
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
-
✓DOI references
Found 2 DOI reference(s) in README -
✓Academic publication links
Links to: arxiv.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.5%) to scientific vocabulary
Repository
Repository for the NeurIPS2021 paper "Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions"
Basic Info
- Host: GitHub
- Owner: ZIB-IOL
- License: mit
- Language: Julia
- Default Branch: main
- Size: 37.1 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions
Repository for the paper "Simple steps are all you need: Frank-Wolfe and generalized self-concordant functions", NeurIPS 2021.
Find the preprint here, cite with the CITATION.bib entry.
The step sizes developed in the paper are available in the FrankWolfe.jl package as MonotonicStepSize and MonotonicGenericStepsize.
Due to their large size, the raw instance data files are not included in the repository but available on the Zenodo archive.
Run the get_data_instances.sh bash script (or equivalent on your system) to fetch them.
If wget or unzip are not available for you, download data.zip from the URL and place the data folder at the top-level of this repository.
plotting/plot_experiment_results.py is used to generate the figures stored in Images/.
Repository structure:
├── data # raw instance data obtained from get_data_instances.sh
├── Images # Final images
├── plotting # Plotting script
└── results # result JSON files
All top-level scripts generate data or results.
Requirements
The recommended Julia version is 1.6, the Project.toml and Manifest.toml should be used to instantiate the environment.
The Python plotting script was run on Python 3.7.9 with matplotlib 3.3.3.
Owner
- Name: IOL Lab
- Login: ZIB-IOL
- Kind: organization
- Location: Germany
- Website: https://iol.zib.de
- Repositories: 27
- Profile: https://github.com/ZIB-IOL
Working on optimization and learning at the intersection of mathematics and computer science
Citation (CITATION.bib)
@article{carderera2021simple,
title={Simple steps are all you need: {F}rank-{W}olfe and generalized self-concordant functions},
author={Carderera, Alejandro and Besan{\c{c}}on, Mathieu and Pokutta, Sebastian},
journal={Advances in Neural Information Processing Systems},
volume={34},
pages={5390--5401},
year={2021}
}
GitHub Events
Total
Last Year
Issues and Pull Requests
Last synced: 11 months ago
All Time
- Total issues: 0
- Total pull requests: 1
- Average time to close issues: N/A
- Average time to close pull requests: 1 minute
- Total issue authors: 0
- Total pull request authors: 1
- Average comments per issue: 0
- Average comments per pull request: 0.0
- Merged pull requests: 1
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
- matbesancon (1)