pyrfm 0.4.1

Random Feature Method (RFM) tools in Python

A Python package for Random Feature Method (RFM)

Quick Install

conda create -n pyRFM python=3.10 -y
conda activate pyRFM
pip install pyrfm

To get the source code and examples, you can clone the repository:

git clone https://github.com/IFaay/pyRFM.git
cd pyRFM

Update

pip install --upgrade --force-reinstall pyrfm
# git pull  # Update local source

and re-download / pull the source code.

Remark

All examples run successfully on a host equipped with 8GB of GPU memory and 32GB of RAM. Example scripts are located in the examples folder.

Reference

[1] J. Chen, X. Chi, W. E, and Z. Yang, “Bridging traditional and machine learning-based algorithms for solving pdes: The random feature method,” J. Mach. Learn., vol. 1, no. 3, pp. 268–298, 2022, doi: 10.4208/jml.220726.

[2] J. Chen, W. E, and Y. Luo, “The random feature method for time-dependent problems,” East Asian Journal on Applied Mathematics, vol. 13, no. 3, pp. 435–463, 2023, doi: 10.4208/eajam.2023-065.050423.

[3] J. Chen, W. E, and Y. Sun, “Optimization of Random Feature Method in the High-Precision Regime,” Com Appl Math Comput, Mar. 2024, doi: 10.1007/s42967-024-00389-8.

You can cite this package as:

[4] J. Chen and Y. Sun, “pyRFM: A High-Performance Python Implementation of the Random Feature Method with Applications,” Journal on Numerical Methods and Computer Applications, vol. 47, no. 2, Jun. 2026, doi: 10.12288/szjs.j2025-1045.

@article{chen_pyrfm_2026,
  title = {{{pyRFM}}: {{A High-Performance Python Implementation}} of the {{Random Feature Method}} with {{Applications}}},
  author = {Chen, Jingrun and Sun, Yifei},
  year = 2026,
  month = jun,
  journal = {Journal on Numerical Methods and Computer Applications},
  volume = {47},
  number = {2},
  doi = {10.12288/szjs.j2025-1045},
}