tf_privacy.make_keras_optimizer_class
Stay organized with collections
Save and categorize content based on your preferences.
Returns a differentially private optimizer using the GaussianSumQuery.
tf_privacy.make_keras_optimizer_class(
cls: Type[tf.keras.optimizers.Optimizer]
)
For backwards compatibility, we create this symbol to match the previous
output of make_keras_optimizer_class but using the new logic.
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.
Last updated 2024-02-16 UTC.
[null,null,["Last updated 2024-02-16 UTC."],[],[],null,["# tf_privacy.make_keras_optimizer_class\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/privacy/blob/v0.9.0/privacy/privacy/optimizers/dp_optimizer_keras.py#L570-L585) |\n\nReturns a differentially private optimizer using the `GaussianSumQuery`. \n\n tf_privacy.make_keras_optimizer_class(\n cls: Type[tf.keras.optimizers.Optimizer]\n )\n\nFor backwards compatibility, we create this symbol to match the previous\noutput of `make_keras_optimizer_class` but using the new logic.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `cls` | Class from which to derive a DP subclass. Should be a subclass of [`tf.keras.optimizers.Optimizer`](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers/Optimizer). |\n\n\u003cbr /\u003e"]]
View source on GitHub