View source on GitHub
|
Represents an application of the Gaussian mechanism.
Inherits From: DpEvent
tf_privacy.GaussianDpEvent(
noise_multiplier
)
For values v_i and noise z ~ N(0, s^2I), this mechanism returns sum_i v_i + z. If the norms of the values are bounded ||v_i|| <= C, the noise_multiplier is defined as s / C.
Attributes | |
|---|---|
noise_multiplier
|
|
Methods
__eq__
__eq__(
other
)
Method generated by attrs for class GaussianDpEvent.
__ge__
__ge__(
other
)
Method generated by attrs for class GaussianDpEvent.
__gt__
__gt__(
other
)
Method generated by attrs for class GaussianDpEvent.
__le__
__le__(
other
)
Method generated by attrs for class GaussianDpEvent.
__lt__
__lt__(
other
)
Method generated by attrs for class GaussianDpEvent.
__ne__
__ne__(
other
)
Method generated by attrs for class GaussianDpEvent.