madgrad

Here are 4 public repositories matching this topic...

optimizer & lr scheduler & loss function collections in PyTorch

deep-learning sam optimizer pytorch ranger muon loss-functions lookahead scion learning-rate-scheduling radam diffgrad gradient-centralization adamp adabelief madgrad adan adai ademamix

Implementation of our paper "Wasserstein Adversarial Transformer for Cloud Workload Prediction"

Super-Convergence on CIFAR10

Provide a collection of flexible learning rate schedulers for PyTorch with presets, warmup wrappers, and research-based implementations.

Add a description, image, and links to the madgrad topic page so that developers can more easily learn about it.

To associate your repository with the madgrad topic, visit your repo's landing page and select "manage topics."