conjugate-gradient
Python wrapper for CG_DESCENT.
This package implements some optimization methods used in numerical optimiation tasks for neural networks that aren't usually implemented in deep learning frameworks because of their computational constraints.
(Python, R, C/C++) Minimize a function subject to non-negativity constraints on variables (conjugate gradient)
Linear solvers and eigendecomposition for AWS Trainium via NKI (cuSOLVER-equivalent) — Jacobi eigh, Cholesky/LU/QR factorizations, CG/GMRES iterative solvers, Newton-Schulz inverse square root.
A Python implementation of a conjugate gradient algorithm (GPCG) for solving bound-constrained quadratic programs.
