yinleung/FSGDM

[ICLR 2025] On the Performance Analysis of Momentum Method: A Frequency Domain Perspective

/ 100

Emerging

This project offers an advanced optimizer for training deep neural networks, especially for tasks like image classification. It takes your model's parameters and training data, and outputs a more effectively trained model by dynamically adjusting how gradients are processed. Data scientists, machine learning engineers, and researchers working on deep learning models would find this valuable.

No commits in the last 6 months. Available on PyPI.

Use this if you are training deep learning models and want to improve convergence and performance by leveraging an optimizer that intelligently filters gradient components.

Not ideal if you are not working with deep learning models, or if you prefer a simpler, less configurable optimizer without needing fine-tuned control over gradient frequency components.

deep-learning-training image-classification neural-network-optimization model-training machine-learning-research

Stale 6m

Maintenance 0 / 25

Adoption 5 / 25

Maturity 25 / 25

Community 0 / 25

How are scores calculated?

Stars

Forks

—

Language

Python

License

Apache-2.0

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)

Explore ML Frameworks

All categories Trending ML Framework directory Insights