jwetzl/CudaLBFGS

This is a cross-platform, CUDA-based C++ library for general-purpose, unconstrained nonlinear optimization on the GPU. It implements the L-BFGS (“Limited-memory Broyden-Fletcher-Goldfarb-Shanno“) method, a popular Quasi-Newton variant with a low memory footprint.

语言：Objective-C · GitHub 星标：139 · Fork：41

在 GitHub 上查看原仓库