<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/distributions/__init__.py) |

TensorFlow Probability experimental distributions package.

## Modules

[`marginal_fns`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/marginal_fns) module: Experimental functions to use as marginals for GaussianProcess(es).

## Classes

[`class ImportanceResample`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/ImportanceResample): Models the distribution of finitely many importance-reweighted samples.

[`class IncrementLogProb`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/IncrementLogProb): A distribution representing an unnormalized measure on a singleton set.

[`class JointDistributionPinned`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/JointDistributionPinned): A wrapper class for `JointDistribution` which pins, e.g., the evidence.

[`class MultiTaskGaussianProcess`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/MultiTaskGaussianProcess): Marginal distribution of a Multitask GP at finitely many points.

[`class MultiTaskGaussianProcessRegressionModel`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/MultiTaskGaussianProcessRegressionModel): Posterior predictive in a conjugate Multi-task GP regression model.

[`class MultivariateNormalPrecisionFactorLinearOperator`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/MultivariateNormalPrecisionFactorLinearOperator): A multivariate normal on `R^k`, parametrized by a precision factor.

## Functions

[`inflated_factory(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/inflated_factory): Create Inflated subclasses for specific distributions and positions.

[`log_prob_ratio(...)`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/distributions/log_prob_ratio): Computes `p.log_prob(x) - q.log_prob(y)`, numerically stably.