Data

Tools

Indexes

Applications

Experiments

Open Source Science

affineinvariantolfw

Code for the paper Accelerated Affine-Invariant Vonvergence Rates of the Frank-Wolfe Algorithm with Open-Loop Step-Sizes

https://github.com/zib-iol/affineinvariantolfw

Science Score: 41.0%

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
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.5%) to scientific vocabulary

Keywords

frank-wolfe
Last synced: 6 months ago · JSON representation ·

Repository

Code for the paper Accelerated Affine-Invariant Vonvergence Rates of the Frank-Wolfe Algorithm with Open-Loop Step-Sizes

Basic Info
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
frank-wolfe
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Accelerated Affine-Invariant Convergence Rates of the Frank-Wolfe Algorithm with Open-Loop Step-Sizes

References

Code for the paper:

Wirth, E., Pena, J., and Pokutta, S. (2023b). Accelerated affine-invariant convergence rates of the Frank-Wolfe algorithm with open-loop step-sizes. arXiv preprint arXiv:2310.04096.

This project is an extension of the previously published Git repository openloopfw, which contains the code to the following paper:

Wirth, E., Pokutta, S., and Kerdreux, T. (2023). Acceleration of Frank-Wolfe Algorithms with Open-Loop Step-Sizes. In Proceedings of AISTATS.

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 affineinvariantopenloopfw.

Activate the conda environment with: shell script $ conda activate affine_invariant_open_loop_fw Navigate to ~/tmp

To perform the experiments in the paper:

```python3 script

python3 -m experiments.ablationstudyl python3 script python3 -m experiments.collaborativefiltering python3 script python3 -m experiments.gapsgrowth python3 script python3 -m experiments.logisticregression python3 script python3 -m experiments.polytopelsol python3 script python3 -m experiments.polytope python3 script python3 -m experiments.regression python3 script python3 -m experiments.stronggrowth python3 script python3 -m experiments.weakboundarygrowth ```

The experiments are then stored in ~/tmp/experiments/figures.

Some referees were interested in seeing the effects of higher dimensions on the experiments. No surprises occurred. For completeness, the additional experiments can be run in the same way as the experiments for the main paper: ```python3 script

python3 -m experiments.refereeablationstudyl python3 script python3 -m experiments.refereepolytopelsol ```

Owner

  • Name: IOL Lab
  • Login: ZIB-IOL
  • Kind: organization
  • Location: Germany

Working on optimization and learning at the intersection of mathematics and computer science

Citation (CITATIONS.bib) 

@article{wirth2023accelerated,
      title={Accelerated Affine-Invariant Convergence Rates of the {F}rank-{W}olfe Algorithm with Open-Loop Step-Sizes}, 
      author={Elias Wirth and Javier Pena and Sebastian Pokutta},
      journal={arXiv preprint arXiv:2310.04096},
      year={2023}
}

GitHub Events

Total
Last Year

Issues and Pull Requests

Last synced: 11 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total 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
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
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

environment.yml conda
  • _libgcc_mutex 0.1
  • argon2-cffi 20.1.0
  • async_generator 1.10
  • attrs 21.2.0
  • autograd 1.3
  • backcall 0.2.0
  • blas 1.0
  • bleach 4.0.0
  • bottleneck 1.3.2
  • ca-certificates 2023.01.10
  • certifi 2022.12.7
  • cffi 1.14.6
  • cycler 0.10.0
  • dbus 1.13.18
  • decorator 5.0.9
  • defusedxml 0.7.1
  • entrypoints 0.3
  • expat 2.3.0
  • fontconfig 2.13.1
  • freetype 2.10.4
  • future 0.18.2
  • glib 2.68.1
  • gst-plugins-base 1.14.0
  • gstreamer 1.14.0
  • icu 58.2
  • importlib-metadata 3.10.0
  • importlib_metadata 3.10.0
  • intel-openmp 2021.2.0
  • ipykernel 5.3.4
  • ipython 7.24.0
  • ipython_genutils 0.2.0
  • ipywidgets 7.6.3
  • jedi 0.18.0
  • jinja2 3.0.1
  • joblib 1.0.1
  • jpeg 9b
  • jsonschema 3.2.0
  • jupyter 1.0.0
  • jupyter_client 6.1.12
  • jupyter_console 6.4.0
  • jupyter_core 4.7.1
  • jupyterlab_pygments 0.1.2
  • jupyterlab_widgets 1.0.0
  • kiwisolver 1.3.1
  • lcms2 2.12
  • ld_impl_linux-64 2.33.1
  • libffi 3.3
  • libgcc-ng 9.1.0
  • libgfortran-ng 7.3.0
  • libpng 1.6.37
  • libsodium 1.0.18
  • libstdcxx-ng 9.1.0
  • libtiff 4.1.0
  • libuuid 1.0.3
  • libxcb 1.14
  • libxml2 2.9.10
  • lz4-c 1.9.3
  • markupsafe 2.0.1
  • matplotlib 3.3.4
  • matplotlib-base 3.3.4
  • matplotlib-inline 0.1.2
  • mistune 0.8.4
  • mkl 2021.2.0
  • mkl-service 2.3.0
  • mkl_fft 1.3.0
  • mkl_random 1.2.1
  • nbclient 0.5.3
  • nbconvert 6.1.0
  • nbformat 5.1.3
  • ncurses 6.2
  • nest-asyncio 1.5.1
  • notebook 6.4.3
  • numexpr 2.7.3
  • numpy 1.20.1
  • numpy-base 1.20.1
  • olefile 0.46
  • openssl 1.1.1t
  • packaging 21.0
  • pandas 1.3.3
  • pandocfilters 1.4.3
  • parso 0.8.2
  • patsy 0.5.2
  • pcre 8.44
  • pexpect 4.8.0
  • pickleshare 0.7.5
  • pillow 8.2.0
  • pip 21.0.1
  • prometheus_client 0.11.0
  • prompt-toolkit 3.0.17
  • prompt_toolkit 3.0.17
  • ptyprocess 0.7.0
  • pycparser 2.20
  • pygments 2.9.0
  • pyparsing 2.4.7
  • pyqt 5.9.2
  • pyrsistent 0.18.0
  • python 3.9.4
  • python-dateutil 2.8.1
  • python_abi 3.9
  • pytz 2021.3
  • pyzmq 22.2.1
  • qt 5.9.7
  • qtconsole 5.1.0
  • qtpy 1.9.0
  • readline 8.1
  • scikit-learn 0.24.2
  • scipy 1.6.2
  • send2trash 1.5.0
  • setuptools 52.0.0
  • sip 4.19.13
  • six 1.15.0
  • sqlite 3.35.4
  • statsmodels 0.12.2
  • terminado 0.9.4
  • testpath 0.5.0
  • threadpoolctl 2.1.0
  • tk 8.6.10
  • tornado 6.1
  • traitlets 5.0.5
  • tzdata 2020f
  • wcwidth 0.2.5
  • webencodings 0.5.1
  • wheel 0.36.2
  • widgetsnbextension 3.5.1
  • xz 5.2.5
  • zeromq 4.3.4
  • zipp 3.5.0
  • zlib 1.2.11
  • zstd 1.4.9