PyTorch optimizer based on nonlinear conjugate gradient method

keywords: nonlinear optimization, pattern search, augmented lagrangian, karush-kuhn-tucker, constrained optimization, conjugate gradient methods, quasi newton methods, line search descent methods, onedimensional and multidimensional optimazation

A python package that extends PyTorch by providing Conjugate Gradient optimization algorithms.

C++ implementation of the Fletcher-Reeves method

An application for visualizing and comparing the work of multidimensional optimization methods with using derivative of the objective function: Gradient Descent Method, Newton Method, Fletcher-Reeves Method.