# tf_privacy.QuantileAdaptiveClipSumQuery

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L25-L145) |

`DPQuery` for Gaussian sum queries with adaptive clipping.

Inherits From: [`SumAggregationDPQuery`](https://www.tensorflow.org/responsible_ai/privacy/api_docs/python/tf_privacy/SumAggregationDPQuery), [`DPQuery`](https://www.tensorflow.org/responsible_ai/privacy/api_docs/python/tf_privacy/DPQuery)

    tf_privacy.QuantileAdaptiveClipSumQuery(
        initial_l2_norm_clip,
        noise_multiplier,
        target_unclipped_quantile,
        learning_rate,
        clipped_count_stddev,
        expected_num_records,
        geometric_update=True
    )

Clipping norm is tuned adaptively to converge to a value such that a specified
quantile of updates are clipped, using the algorithm of Andrew et al. (
<https://arxiv.org/abs/1905.03871>). See the paper for details and suggested
hyperparameter settings.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `initial_l2_norm_clip` | The initial value of clipping norm. |
| `noise_multiplier` | The stddev of the noise added to the output will be this times the current value of the clipping norm. |
| `target_unclipped_quantile` | The desired quantile of updates which should be unclipped. I.e., a value of 0.8 means a value of l2_norm_clip should be found for which approximately 20% of updates are clipped each round. Andrew et al. recommends that this be set to 0.5 to clip to the median. |
| `learning_rate` | The learning rate for the clipping norm adaptation. With geometric updating, a rate of r means that the clipping norm will change by a maximum factor of exp(r) at each round. This maximum is attained when \|actual_unclipped_fraction - target_unclipped_quantile\| is 1.0. Andrew et al. recommends that this be set to 0.2 for geometric updating. |
| `clipped_count_stddev` | The stddev of the noise added to the clipped_count. Andrew et al. recommends that this be set to `expected_num_records / 20` for reasonably fast adaptation and high privacy. |
| `expected_num_records` | The expected number of records per round, used to estimate the clipped count quantile. |
| `geometric_update` | If `True`, use geometric updating of clip (recommended). |

<br />

## Methods

### `accumulate_preprocessed_record`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/dp_query.py#L292-L295)

    accumulate_preprocessed_record(
        sample_state, preprocessed_record
    )

Implements `tensorflow_privacy.DPQuery.accumulate_preprocessed_record`.

### `accumulate_record`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/dp_query.py#L187-L210)

    accumulate_record(
        params, sample_state, record
    )

Accumulates a single record into the sample state.

This is a helper method that simply delegates to `preprocess_record` and
`accumulate_preprocessed_record` for the common case when both of those
functions run on a single device. Typically this will be a simple sum.

<br />

<br />

<br />

| Args ||
|---|---|
| `params` | The parameters for the sample. In standard DP-SGD training, the clipping norm for the sample's microbatch gradients (i.e., a maximum norm magnitude to which each gradient is clipped) |
| `sample_state` | The current sample state. In standard DP-SGD training, the accumulated sum of previous clipped microbatch gradients. |
| `record` | The record to accumulate. In standard DP-SGD training, the gradient computed for the examples in one microbatch, which may be the gradient for just one example (for size 1 microbatches). |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The updated sample state. In standard DP-SGD training, the set of previous microbatch gradients with the addition of the record argument. ||

<br />

### `derive_metrics`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L143-L145)

    derive_metrics(
        global_state
    )

Returns the current clipping norm as a metric.

### `derive_sample_params`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L97-L102)

    derive_sample_params(
        global_state
    )

Implements `tensorflow_privacy.DPQuery.derive_sample_params`.

### `get_noised_result`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L120-L141)

    get_noised_result(
        sample_state, global_state
    )

Implements `tensorflow_privacy.DPQuery.get_noised_result`.

### `initial_global_state`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L90-L95)

    initial_global_state()

Implements `tensorflow_privacy.DPQuery.initial_global_state`.

### `initial_sample_state`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L104-L108)

    initial_sample_state(
        template
    )

Implements `tensorflow_privacy.DPQuery.initial_sample_state`.

### `merge_sample_states`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/dp_query.py#L297-L299)

    merge_sample_states(
        sample_state_1, sample_state_2
    )

Implements `tensorflow_privacy.DPQuery.merge_sample_states`.

### `preprocess_record`

[View source](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/dp_query/quantile_adaptive_clip_sum_query.py#L110-L118)

    preprocess_record(
        params, record
    )

Implements `tensorflow_privacy.DPQuery.preprocess_record`.