Metadata-Version: 2.1
Name: torchimize
Version: 0.0.11
Summary: Optimization Algorithms using Pytorch
Home-page: http://github.com/hahnec/torchimize
Author: Christopher Hahne
Author-email: inbox@christopherhahne.de
License: GNU GPL V3.0
Description: torchimize contains implementations of the Gauss-Newton and Levenberg-Marquardt optimization algorithms using the PyTorch library. The main motivation for this project is to enable convex optimization on GPUs based on the torch.Tensor class, which (as of 2022) is widely used in the deep learning field. This package features the capability to minimize several least-squares optimization problems at each loop iteration in parallel.
Keywords: pytorch torch optimization mathematical linear programming gauss newton levenberg marquardt
Platform: UNKNOWN
Description-Content-Type: text/x-rst
