tfc.distributions.estimate_tails
Stay organized with collections
Save and categorize content based on your preferences.
Estimates approximate tail quantiles.
tfc.distributions.estimate_tails(
func, target, shape, dtype
)
This runs a simple Adam iteration to determine tail quantiles. The
objective is to find an x such that:
func(x) == target
For instance, if func is a CDF and the target is a quantile value, this
would find the approximate location of that quantile. Note that func is
assumed to be monotonic. When each tail estimate has passed the optimal value
of x, the algorithm does 100 additional iterations and then stops.
This operation is vectorized. The tensor shape of x is given by shape, and
target must have a shape that is broadcastable to the output of func(x).
Args |
|---|
func
|
A callable that computes cumulative distribution function, survival
function, or similar.
|
target
|
The desired target value.
|
shape
|
The shape of the tf.Tensor representing x.
|
dtype
|
The tf.dtypes.Dtype of the computation (and the return value).
|
Returns |
|---|
A tf.Tensor representing the solution (x).
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.
[null,null,["Last updated 2024-04-26 UTC."],[],[],null,["# tfc.distributions.estimate_tails\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/compression/blob/v2.14.1/tensorflow_compression/python/distributions/helpers.py#L29-L101) |\n\nEstimates approximate tail quantiles.\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tfc.estimate_tails`](https://www.tensorflow.org/api_docs/python/tfc/distributions/estimate_tails)\n\n\u003cbr /\u003e\n\n tfc.distributions.estimate_tails(\n func, target, shape, dtype\n )\n\nThis runs a simple Adam iteration to determine tail quantiles. The\nobjective is to find an `x` such that: \n\n func(x) == target\n\nFor instance, if `func` is a CDF and the target is a quantile value, this\nwould find the approximate location of that quantile. Note that `func` is\nassumed to be monotonic. When each tail estimate has passed the optimal value\nof `x`, the algorithm does 100 additional iterations and then stops.\n\nThis operation is vectorized. The tensor shape of `x` is given by `shape`, and\n`target` must have a shape that is broadcastable to the output of `func(x)`.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------|--------------------------------------------------------------------------------------------------------|\n| `func` | A callable that computes cumulative distribution function, survival function, or similar. |\n| `target` | The desired target value. |\n| `shape` | The shape of the [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) representing `x`. |\n| `dtype` | The `tf.dtypes.Dtype` of the computation (and the return value). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor) representing the solution (`x`). ||\n\n\u003cbr /\u003e"]]
View source on GitHub