how to compute the sensitivity

Yangfan-Jiang / Federated-Learning-with-Differential-Privacy

Implementation of dp-based federated learning framework using PyTorch

MIT License

274 stars 53 forks source link

Closed hdadong closed 2 years ago

hdadong commented 3 years ago

why your sensitivity = 2 self.lr self.clip / self.data_size + (self.E - 1) 2 self.lr self.clip? in the paper ,the sensitivity = 2Cpi/m or 2C/m.

Yangfan-Jiang commented 3 years ago