You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
High order and sparse layers in pytorch. Lagrange Polynomial, Piecewise Lagrange Polynomial, Piecewise Discontinuous Lagrange Polynomial (Chebyshev nodes) and Fourier Series layers of arbitrary order. Piecewise implementations could be thought of as a 1d grid (for each neuron) where each grid element is Lagrange polynomial. Both full connected a…
Chebyshev-proxy Rootfinding based on J. Boyd (2013 and 2014). This repository is intended for educational use and isn't really a standalone package; however, the implementation may be enlightening for someone wishing to reimplement the CPR algorithm.
Experimental Python code developed for research on: H. Waclawek and S. Huber, “Machine Learning Optimized Orthogonal Basis Piecewise Polynomial Approximation,” in Learning and Intelligent Optimization, Cham: Springer Nature Switzerland, 2025, pp. 427–441.
A serial, parallel and vectorised version of PLDM dynamics has been implemented. The serial version uses numba to get speedup of a compiled language. The parallel version uses mpi4py to utilise the multiprocessing capability of HPC clusters. The vectorised version uses a wide variety of GPU libraries (cuda, cupy, pytorch) to highly vectorise PLDM.