Differential privacy
DpBudget
dataclass
DpStep
dataclass
Data for differentially private step.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
noise_multiplier
|
float
|
The ratio of the standard deviation of the Gaussian noise to the L2-sensitivity of the gradients to which the noise is added (How much noise to add). |
1.0
|
max_grad_norm
|
float
|
The maximum norm of the per-sample gradients. Any gradient with norm higher than this will be clipped to this value, thus limiting the L2-sensitivity. |
1.0
|
max_batch_size
|
int
|
Maximum size of the physical batch processed during computations. It will not change the size of the logical batch. If <= 0, no cap is imposed on the physical batch. Notice that due to Poisson sampling, the logical batch size during differentially private training is distributed according to a binomial distribution. |
0
|