team-approx-bayes/ivon
IVON optimizer for neural networks based on variational learning.
This is a specialized optimization tool designed to improve how deep neural networks learn and make predictions. It takes your existing neural network setup in PyTorch and trains it using a variational learning approach. The output is a more robust model that can also quantify its uncertainty, which is particularly useful for machine learning engineers and researchers building advanced AI systems.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher working with PyTorch and want to train large deep neural networks to be more robust and provide uncertainty estimates.
Not ideal if you are a beginner looking for a simple, off-the-shelf optimizer for basic neural network tasks, or if you are not working within the PyTorch ecosystem.
Stars
82
Forks
9
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 07, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/team-approx-bayes/ivon"
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.
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)