<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/__init__.py) |

TensorFlow Probability API-unstable package.

This package contains potentially useful code which is under active development
with the intention eventually migrate to TFP proper. All code in
[`tfp.experimental`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental) should be of production quality, i.e., idiomatically
consistent, well tested, and extensively documented. [`tfp.experimental`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental) code
relaxes the TFP non-experimental contract in two regards:

1. [`tfp.experimental`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental) has no API stability guarantee. The public footprint of [`tfp.experimental`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental) code may change without notice or warning.
2. Code outside [`tfp.experimental`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental) cannot depend on code within [`tfp.experimental`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental).

You are welcome to try any of this out (and tell us how well it works for you!).

## Modules

[`auto_batching`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_batching) module: TensorFlow Probability auto-batching package.

[`bayesopt`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bayesopt) module: TensorFlow Probability experimental Bayesopt package.

[`bijectors`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/bijectors) module: TensorFlow Probability experimental bijectors package.

[`distribute`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distribute) module: Experimental module for doing distributed log prob calculations.

[`distributions`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions) module: TensorFlow Probability experimental distributions package.

[`fastgp`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/fastgp) module: Package for training Gaussian Processes in time less than O(n\^3).

[`joint_distribution_layers`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/joint_distribution_layers) module: Experimental Joint Distribution Layers library.

[`linalg`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/linalg) module: Experimental tools for linear algebra.

[`marginalize`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/marginalize) module: Marginalizable probability distributions.

[`math`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/math) module: Experimental math.

[`mcmc`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/mcmc) module: TensorFlow Probability experimental MCMC package.

[`nn`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn) module: Tools for building neural networks.

[`parallel_filter`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/parallel_filter) module: TensorFlow Probability experimental parallel filtering package.

[`psd_kernels`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/psd_kernels) module: TensorFlow Probability experimental PSD kernels package.

[`sequential`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/sequential) module: TensorFlow Probability experimental sequential estimation package.

[`stats`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/stats) module: Statistical functions.

[`sts_gibbs`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/sts_gibbs) module: Gibbs sampling inference for structural time series models.

[`tangent_spaces`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/tangent_spaces) module: TensorFlow Probability experimental tangent spaces package.

[`timeseries`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/timeseries) module: Experimental methods and objectives for variational inference.

[`util`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/util) module: TensorFlow Probability experimental python utilities.

[`vi`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/vi) module: Experimental methods and objectives for variational inference.

## Classes

[`class AutoCompositeTensor`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/AutoCompositeTensor): Recommended base class for `@auto_composite_tensor`-ified classes.

## Functions

[`as_composite(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/as_composite)

[`auto_composite_tensor(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/auto_composite_tensor): Automagically generate `CompositeTensor` behavior for `cls`.

[`register_composite(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/register_composite)