amp-regularizer

Here is 1 public repository matching this topic...

gautamHCSCV / Federated-Learning-Methods-Comparison

We utilize the Adversarial Model Perturbations (AMP) regularizer to regularize clients’ models. The AMP regulzaizer is based on perturbing the model parameters so as to get a more generalized model. The claim of AMP regularizer is to reach flat minima and therefore is expected to reach flat minima in FL settings as well.

scaffold pytorch federated-learning fedavg fedprox fedntd amp-regularizer

Updated May 24, 2023
Python

Add this topic to your repo

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

Learn more