tf_privacy.NoPrivacyAverageQuery

Implements DPQuery interface for an average query with no privacy.

Inherits From: SumAggregationDPQuery, DPQuery

Accumulates vectors and normalizes by the total number of accumulated vectors. Under some sampling schemes, such as Poisson subsampling, the number of records in a sample is a private quantity, so we lose all privacy guarantees by using the number of records directly to normalize.

Also allows weighted accumulation, unlike the base class DPQuery. In a private implementation of weighted average, the weight would have to be itself privatized.

Methods

accumulate_preprocessed_record

View source

accumulate_preprocessed_record(
    sample_state, preprocessed_record
)

Implements tensorflow_privacy.DPQuery.accumulate_preprocessed_record.

accumulate_record

View source

accumulate_record(
    params, sample_state, record, weight=1
)

Implements tensorflow_privacy.DPQuery.accumulate_record.

Optional weight argument allows weighted accumulation.

Args
params	The parameters for the sample.
sample_state	The current sample state.
record	The record to accumulate.
weight	Optional weight for the record.

Returns
The updated sample state.

derive_metrics

View source

derive_metrics(
    global_state
)

Derives metric information from the current global state.

Any metrics returned should be derived only from privatized quantities.

Args
global_state	The global state from which to derive metrics.

Returns
A collections.OrderedDict mapping string metric names to tensor values.

derive_sample_params

View source

derive_sample_params(
    global_state
)

Given the global state, derives parameters to use for the next sample.

For example, if the mechanism needs to clip records to bound the norm, the clipping norm should be part of the sample params. In a distributed context, this is the part of the state that would be sent to the workers so they can process records.

Args
global_state	The current global state.

Returns
Parameters to use to process records in the next sample.

get_noised_result

View source

get_noised_result(
    sample_state, global_state
)

Implements tensorflow_privacy.DPQuery.get_noised_result.

initial_global_state

View source

initial_global_state()

Returns the initial global state for the DPQuery.

The global state contains any state information that changes across repeated applications of the mechanism. The default implementation returns just an empty tuple for implementing classes that do not have any persistent state.

This object must be processable via tf.nest.map_structure.

Returns
The global state.

initial_sample_state

View source

initial_sample_state(
    template
)

Implements tensorflow_privacy.DPQuery.initial_sample_state.

merge_sample_states

View source

merge_sample_states(
    sample_state_1, sample_state_2
)

Implements tensorflow_privacy.DPQuery.merge_sample_states.

preprocess_record

View source

preprocess_record(
    params, record, weight=1
)

Implements tensorflow_privacy.DPQuery.preprocess_record.

Optional weight argument allows weighted accumulation.

Args
params	The parameters for the sample.
record	The record to accumulate.
weight	Optional weight for the record.

Returns
The preprocessed record.