ltatzel/PyTorchHessianFree
PyTorch implementation of the Hessian-free optimizer
This is a PyTorch implementation of the Hessian-free optimizer, a method for efficiently training machine learning models, especially neural networks. It takes a neural network model and its associated loss function as input and outputs optimized model parameters. This tool is for machine learning engineers and researchers who are developing and training large neural networks.
No commits in the last 6 months.
Use this if you are training large neural networks and want a more advanced, memory-efficient optimization method than standard gradient descent.
Not ideal if you are working with small models or datasets where the complexity of this optimizer would outweigh the benefits.
Stars
36
Forks
5
Language
Python
License
BSD-3-Clause
Category
Last pushed
Jun 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ltatzel/PyTorchHessianFree"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nschaetti/EchoTorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...
metaopt/torchopt
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)