The ratio of the (effective) noise stddev to the clip.
The expected total weight of all clients, used as the
denominator for the average computation.
Learning rate for quantile-based adaptive
clipping. If 0, fixed clipping is used. If per_vector_clipping=True and
geometric_clip_update=False, the learning rate of each vector is
proportional to that vector's initial clip.
Target unclipped quantile for adaptive clipping.
The fraction of privacy budget to use for
estimating clipped counts.
The expected number of clients for estimating clipped
If True, clip each weight tensor independently.
Otherwise, global clipping is used. The clipping norm for each vector (or
the initial clipping norm, in the case of adaptive clipping) is
proportional to the sqrt of the vector dimensionality such that the root
sum squared of the individual clips equals clip.
If True, use geometric updating of the clip.
A tff.learning.Model to determine the structure of model weights.
Required only if per_vector_clipping is True.
A DPQuery suitable for use in a call to build_dp_aggregate to perform
Federated Averaging with differential privacy.