ncg-optimizer 0.0.1b0

Pytorch optimizer based on nonlinear conjugate gradient method

NCG-optimizer is a set of optimizer about nonliear conjugate gradient in Pytorch.

Install

$ pip install ncg_optimizer

Example

from ncg-optimizer import PRP

# model = Your Model
optimizer = PRP(model.parameters())

Supported Optimizers

Basic Methods

The implementation of all basic methods is based on the book “Nonlinear Conjugate Gradient Method” [1].

[1]

Y.H. Dai and Y. Yuan (2000), Nonlinear Conjugate Gradient Methods, Shanghai Scientific and Technical Publishers, Shanghai. (in Chinese)

Linear Conjugate Gradient

The linear conjugate gradient(LCG) method is only applicable to linear equation solving problems. It converts linear equations into quadratic functions, so that the problem can be solved iteratively without inverting the coefficient matrix.

Fletcher-Reeves

Changes

0.0.1 (2023-01-01)

• Initial release.

• Added support for LCG, FR, .