Save the date! Google I/O returns May 18-20 Register now


A generic probability distribution base class.

Distribution is a base class for constructing and organizing properties (e.g., mean, variance) of random variables (e.g, Bernoulli, Gaussian).


Subclasses are expected to implement a leading-underscore version of the same-named function. The argument signature should be identical except for the omission of name="...". For example, to enable log_prob(value, name="log_prob") a subclass should implement _log_prob(value).

Subclasses can append to public-level docstrings by providing docstrings for their method specializations. For example:

@util.AppendDocstring("Some other details.")
def _log_prob(self, value):

would add the string "Some other details." to the log_prob function docstring. This is implemented as a simple decorator to avoid python linter complaining about missing Args/Returns/Raises sections in the partial docstrings.

Broadcasting, batching, and shapes

All distributions support batches of independent distributions of that type. The batch shape is determined by broadcasting together the parameters.

The shape of arguments to __init__, cdf, log_cdf, prob, and log_prob reflect this broadcasting, as does the return value of sample and sample_n.

sample_n_shape = [n] + batch_shape + event_shape, where sample_n_shape is the shape of the Tensor returned from sample_n, n is the number of samples, batch_shape defines how many independent distributions there are, and event_shape defines the shape of samples from each of those independent distributions. Samples are independent along the batch_shape dimensions, but not necessarily so along the event_shape dimensions (depending on the particulars of the underlying distribution).

Using the Uniform distribution as an example:

minval = 3.0
maxval = [[4.0, 6.0],
          [10.0, 12.0]]

# Broadcasting:
# This instance represents 4 Uniform distributions. Each has a lower bound at
# 3.0 as the `minval` parameter was broadcasted to match `maxval`'s shape.
u = Uniform(minval, maxval)

# `event_shape` is `TensorShape([])`.
event_shape = u.event_shape
# `event_shape_t` is a `Tensor` which will evaluate to [].
event_shape_t = u.event_shape_tensor()

# Sampling returns a sample per distribution. `samples` has shape
# [5, 2, 2], which is [n] + batch_shape + event_shape, where n=5,
# batch_shape=[2, 2], and event_shape=[].
samples = u.sample_n(5)

# The broadcasting holds across methods. Here we use `cdf` as an example. The
# same holds for `log_cdf` and the likelihood functions.

# `cum_prob` has shape [2, 2] as the `value` argument was broadcasted to the
# shape of the `Uniform` instance.
cum_prob_broadcast = u.cdf(4.0)

# `cum_prob`'s shape is [2, 2], one per distribution. No broadcasting
# occurred.
cum_prob_per_dist = u.cdf([[4.0, 5.0],
                           [6.0, 7.0]])

# INVALID as the `value` argument is not broadcastable to the distribution's
# shape.
cum_prob_invalid = u.cdf([4.0, 5.0, 6.0])


There are three important concepts associated with TensorFlow Distributions shapes:

  • Event shape describes the shape of a single draw from the distribution; it may be dependent across dimensions. For scalar distributions, the event shape is []. For a 5-dimensional MultivariateNormal, the event shape is [5].
  • Batch shape describes independent, not identically distributed draws, aka a "collection" or "bunch" of distributions.
  • Sample shape describes independent, identically distributed draws of batches from the distribution family.

The event shape and the batch shape are properties of a Distribution object, whereas the sample shape is associated with a specific call to sample or log_prob.

For detailed usage examples of TensorFlow Distributions shapes, see this tutorial

Parameter values leading to undefined statistics or distributions.

Some distributions do not have well-defined statistics for all initialization parameter values. For example, the beta distribution is parameterized by positive real numbers concentration1 and concentration0, and does not have well-defined mode if concentration1 < 1 or concentration0 < 1.

The user is given the option of raising an exception or returning NaN.

a = tf.exp(tf.matmul(logits, weights_a))
b = tf.exp(tf.matmul(logits, weights_b))

# Will raise exception if ANY batch member has a < 1 or b < 1.
dist = distributions.beta(a, b, allow_nan_stats=False)
mode = dist.mode().eval()

# Will return NaN for batch members with either a < 1 or b < 1.
dist = distributions.beta(a, b, allow_nan_stats=True)  # Default behavior
mode = dist.mode().eval()

In all cases, an exception is raised if invalid parameters are passed, e.g.

# Will raise an exception if any Op is run.
negative_a = -1.0 * a  # beta distribution by definition has a > 0.
dist = distributions.beta(negative_a, b, allow_nan_stats=True)

dtype The type of the event samples. None implies no type-enforcement.
reparameterization_type Instance of ReparameterizationType. If distributions.FULLY_REPARAMETERIZED, this Distribution can be reparameterized in terms of some standard distribution with a function whose Jacobian is constant for the support of the standard distribution. If distributions.NOT_REPARAMETERIZED, then no such reparameterization is available.
validate_args Python bool, default False. When True distribution parameters are checked for validity despite possibly degrading runtime performance. When False invalid inputs may silently render incorrect outputs.
allow_nan_stats Python bool, default True. When True, statistics (e.g., mean, mode, variance) use the value "NaN" to indicate the result is undefined. When False, an exception is raised if one or more of the statistic's batch members are undefined.
parameters Python dict of parameters used to instantiate this Distribution.
graph_parents Python list of graph prerequisites of this Distribution.
name Python str name prefixed to Ops created by this class. Default: subclass name.

ValueError if any member of graph_parents is None or not a Tensor.

allow_nan_stats Python bool describing behavior when a stat is undefined.

Stats return +/- infinity when it makes sense. E.g., the variance of a Cauchy distribution is infinity. However, sometimes the statistic is undefined, e.g., if a distribution's pdf does not achieve a maximum within the support of the distribution, the mode is undefined. If the mean is undefined, then by definition the variance is undefined. E.g. the mean for Student's T for df = 1 is undefined (no clear way to say it is either + or - infinity), so the variance = E[(X - mean)**2] is also undefined.

batch_shape Shape of a single sample from a single event index as a TensorShape.

May be partially defined or unknown.

The batch dimensions are indexes into independent, non-identical parameterizations of this distribution.

dtype The DType of Tensors handled by this Distribution.
event_shape Shape of a single sample from a single batch as a TensorShape.

May be partially defined or unknown.

name Name prepended to all ops created by this Distribution.
parameters Dictionary of parameters used to instantiate this Distribution.
reparameterization_type Describes how samples from the distribution are reparameterized.

Currently this is one of the static instances distributions.FULLY_REPARAMETERIZED or distributions.NOT_REPARAMETERIZED.

validate_args Python bool indicating possibly expensive checks are enabled.



View source

Shape of a single sample from a single event index as a 1-D Tensor.

The batch dimensions are indexes into independent, non-identical parameterizations of this distribution.

name name to give to the op

batch_shape Tensor.


View source

Cumulative distribution function.

Given random variable X, the cumulative distribution function cdf is:

cdf(x) := P[X <= x]

value float or double Tensor.
name Python str prepended to names of ops created by this function.

cdf a Tensor of shape sample_shape(x) + self.batch_shape with values of type self.dtype.


View source

Creates a deep copy of the distribution.

**override_parameters_kwargs String/value dictionary of initialization arguments to override with new values.

distribution A new instance of type(self) initialized from the union of self.parameters and override_parameters_kwargs, i.e., dict(self.parameters, **override_parameters_kwargs).


View source


Covariance is (possibly) defined only for non-scalar-event distributions.

For example, for a length-k, vector-valued distribution, it is calculated as,

Cov[i, j] = Covariance(X_i, X_j) = E[(X_i - E[X_i]) (X_j - E[X_j])]

where Cov is a (batch of) k x k matrix, 0 <= (i, j) < k, and E denotes expectation.

Alternatively, for non-vector, multivariate distributions (e.g., matrix-valued, Wishart), Covariance shall return a (batch of) matrices under some vectorization of the events, i.e.,

Cov[i, j] = Covariance(Vec(X)_i, Vec(X)_j) = [as above]

where Cov is a (batch of) k' x k' matrices, 0 <= (i, j) < k' = reduce_prod(event_shape), and Vec is some function mapping indices of this distribution's event dimensions to indices of a length-k' vector.

name Python str prepended to names of ops created by this function.

covariance Floating-point Tensor with shape [B1, ..., Bn, k', k'] where the first n dimensions are batch coordinates and k' = reduce_prod(self.event_shape).


View source

Computes the (Shannon) cross entropy.

Denote this distribution (self) by P and the other distribution by Q. Assuming P, Q are absolutely continuous with respect to one another and permit densities p(x) dr(x) and q(x) dr(x), (Shanon) cross entropy is defined as:

H[P, Q] = E_p[-log q(X)] = -int_F p(x) log q(x) dr(x)

where F denotes the support of the random variable X ~ P.

other tfp.distributions.Distribution instance.
name Python str prepended to names of ops created by this function.

cross_entropy self.dtype Tensor with shape [B1, ..., Bn] representing n different calculations of (Shanon) cross entropy.


View source

Shannon entropy in nats.


View source

Shape of a single sample from a single batch as a 1-D int32 Tensor.

name name to give to the op

event_shape Tensor.


View source

Indicates that batch_shape == [].

name Python str prepended to names of ops created by this function.

is_scalar_batch bool scalar Tensor.


View source

Indicates that event_shape == [].

name Python str prepended to names of ops created by this function.

is_scalar_event bool scalar Tensor.


View source

Computes the Kullback--Leibler divergence.

Denote this distribution (self) by p and the other distribution by q. Assuming p, q are absolutely continuous with respect to reference measure r, the KL divergence is defined as: