[](https://zenodo.org/doi/10.5281/zenodo.10677187)
[](https://badge.fury.io/py/torchdecomp)
# PyTorchDecomp
A set of matrix decomposition algorithms implemented as PyTorch classes
## Installation
Because PyTorchDecomp is a PyPI package, please install it by `pip` command as follows:
```shell
python -m venv env
pip install torchdecomp
```
For the other OS-specific or package-manager-specific installation, please check the [README.md](https://github.com/pytorch/pytorch) of PyTorch.
## Usage
See the [tutorials](https://chiba-ai-med.github.io/PyTorchDecomp/tutorials.html).
## References
- **LU/QR/Cholesky/Eigenvalue Decomposition**
- Gene H. Golub, Charles F. Van Loan Matrix Computations (Johns Hopkins Studies in the Mathematical Sciences)
- **Principal Component Analysis (PCA) / Partial Least Squares (PLS)**
- R. Arora, A. Cotter, K. Livescu and N. Srebro, Stochastic optimization for PCA and PLS, 2012 50th Annual Allerton Conference on Communication, Control, and Computing, 2012, 861-868. 2012
- **Independent Component Analysis (ICA)**
- Hybarinen, A. and Oja, E. Independent component analysis: algorithms and applications, Neural Networks, 13, 411-430. 2000
- **Deep Deterministic ICA (DDICA)**
- H. Li, S. Yu and J. C. PrÃncipe, Deep Deterministic Independent Component Analysis for Hyperspectral Unmixing, 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3878-3882, 2022
- **Non-negative Matrix Factorization (NMF)**
- Kimura, K. A Study on Efficient Algorithms for Nonnegative Matrix/Tensor Factorization, Ph.D. Thesis, 2017
- **Exponent term depending on Beta parameter**
- Nakano, M. et al., Convergence-guaranteed multiplicative algorithms for nonnegative matrix factorization with Beta-divergence. IEEE MLSP, 283-288, 2010
- **Beta-divergence NMF and Backpropagation**
- https://yoyololicon.github.io/posts/2021/02/torchnmf-algorithm/
## Contributing
If you have suggestions for how `PyTorchDecomp` could be improved, or want to report a bug, open an issue! We'd love all and any contributions.
For more, check out the [Contributing Guide](https://github.com/chiba-ai-med/PyTorchDecomp/blob/main/CONTRIBUTING.md).
## License
PyTorchDecomp has a MIT license, as found in the [LICENSE](https://github.com/chiba-ai-med/PyTorchDecomp/blob/main/LICENSE) file.
## Authors
- Koki Tsuyuzaki
Raw data
{
"_id": null,
"home_page": "https://github.com/chiba-ai-med/PyTorchDecomp",
"name": "torchdecomp",
"maintainer": "Koki Tsuyuzaki",
"docs_url": null,
"requires_python": "<4.0,>=3.10",
"maintainer_email": "k.t.the-answer@hotmail.co.jp",
"keywords": "pytorch, machine learning",
"author": "Koki Tsuyuzaki",
"author_email": "k.t.the-answer@hotmail.co.jp",
"download_url": "https://files.pythonhosted.org/packages/07/29/0f0f8f15b9b69fbd24c8b8195e7265b2d7c99aa874a7dfd924647a1e224a/torchdecomp-1.3.4.tar.gz",
"platform": null,
"description": "[](https://zenodo.org/doi/10.5281/zenodo.10677187)\n[](https://badge.fury.io/py/torchdecomp)\n\n\n\n# PyTorchDecomp\nA set of matrix decomposition algorithms implemented as PyTorch classes\n\n\n## Installation\n\nBecause PyTorchDecomp is a PyPI package, please install it by `pip` command as follows:\n\n```shell\npython -m venv env\npip install torchdecomp\n```\n\nFor the other OS-specific or package-manager-specific installation, please check the [README.md](https://github.com/pytorch/pytorch) of PyTorch.\n\n\n## Usage\n\nSee the [tutorials](https://chiba-ai-med.github.io/PyTorchDecomp/tutorials.html).\n\n## References\n\n- **LU/QR/Cholesky/Eigenvalue Decomposition**\n - Gene H. Golub, Charles F. Van Loan Matrix Computations (Johns Hopkins Studies in the Mathematical Sciences)\n- **Principal Component Analysis (PCA) / Partial Least Squares (PLS)**\n - R. Arora, A. Cotter, K. Livescu and N. Srebro, Stochastic optimization for PCA and PLS, 2012 50th Annual Allerton Conference on Communication, Control, and Computing, 2012, 861-868. 2012\n- **Independent Component Analysis (ICA)**\n - Hybarinen, A. and Oja, E. Independent component analysis: algorithms and applications, Neural Networks, 13, 411-430. 2000\n- **Deep Deterministic ICA (DDICA)**\n - H. Li, S. Yu and J. C. Pr\u00edncipe, Deep Deterministic Independent Component Analysis for Hyperspectral Unmixing, 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 3878-3882, 2022\n- **Non-negative Matrix Factorization (NMF)**\n - Kimura, K. A Study on Efficient Algorithms for Nonnegative Matrix/Tensor Factorization, Ph.D. Thesis, 2017\n - **Exponent term depending on Beta parameter**\n - Nakano, M. et al., Convergence-guaranteed multiplicative algorithms for nonnegative matrix factorization with Beta-divergence. IEEE MLSP, 283-288, 2010\n - **Beta-divergence NMF and Backpropagation**\n - https://yoyololicon.github.io/posts/2021/02/torchnmf-algorithm/\n\n## Contributing\n\nIf you have suggestions for how `PyTorchDecomp` could be improved, or want to report a bug, open an issue! We'd love all and any contributions.\n\nFor more, check out the [Contributing Guide](https://github.com/chiba-ai-med/PyTorchDecomp/blob/main/CONTRIBUTING.md).\n\n\n## License\n\nPyTorchDecomp has a MIT license, as found in the [LICENSE](https://github.com/chiba-ai-med/PyTorchDecomp/blob/main/LICENSE) file.\n\n\n## Authors\n- Koki Tsuyuzaki\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "A set of matrix decomposition algorithms implemented as PyTorch classes",
"version": "1.3.4",
"project_urls": {
"Homepage": "https://github.com/chiba-ai-med/PyTorchDecomp",
"Repository": "https://github.com/chiba-ai-med/PyTorchDecomp"
},
"split_keywords": [
"pytorch",
" machine learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f89664dc1076ca1cfd6de3330946044b0f448db4073ca16decbb0b73801b1c3e",
"md5": "1892aff9c4d55a93220e0515816862ff",
"sha256": "3fc0f984c903937d387a98a38a04b4301d23f7bfb6f4bc8764bb2d0293bdd27b"
},
"downloads": -1,
"filename": "torchdecomp-1.3.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "1892aff9c4d55a93220e0515816862ff",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.10",
"size": 17022,
"upload_time": "2024-06-20T06:11:24",
"upload_time_iso_8601": "2024-06-20T06:11:24.011768Z",
"url": "https://files.pythonhosted.org/packages/f8/96/64dc1076ca1cfd6de3330946044b0f448db4073ca16decbb0b73801b1c3e/torchdecomp-1.3.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "07290f0f8f15b9b69fbd24c8b8195e7265b2d7c99aa874a7dfd924647a1e224a",
"md5": "4c932c6909fc706241e44764d377db86",
"sha256": "6085353579f82f171b840b4902beeee149a83b51a53e31819809c1090124d400"
},
"downloads": -1,
"filename": "torchdecomp-1.3.4.tar.gz",
"has_sig": false,
"md5_digest": "4c932c6909fc706241e44764d377db86",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.10",
"size": 11712,
"upload_time": "2024-06-20T06:11:26",
"upload_time_iso_8601": "2024-06-20T06:11:26.185461Z",
"url": "https://files.pythonhosted.org/packages/07/29/0f0f8f15b9b69fbd24c8b8195e7265b2d7c99aa874a7dfd924647a1e224a/torchdecomp-1.3.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-20 06:11:26",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "chiba-ai-med",
"github_project": "PyTorchDecomp",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "torchdecomp"
}
JSON
