tf.contrib.distributions.bijectors.SoftmaxCentered

Class SoftmaxCentered

Inherits From: Bijector

Defined in tensorflow/contrib/distributions/python/ops/bijectors/softmax_centered.py.

See the guide: Random variable transformations (contrib) > Bijectors

Bijector which computes Y = g(X) = exp([X 0]) / sum(exp([X 0])).

To implement softmax as a bijection, the forward transformation appends a value to the input and the inverse removes this coordinate. The appended coordinate represents a pivot, e.g., softmax(x) = exp(x-c) / sum(exp(x-c)) where c is the implicit last coordinate.

Example Use:

bijector.SoftmaxCentered().forward(tf.log([2, 3, 4]))
# Result: [0.2, 0.3, 0.4, 0.1]
# Extra result: 0.1

bijector.SoftmaxCentered().inverse([0.2, 0.3, 0.4, 0.1])
# Result: tf.log([2, 3, 4])
# Extra coordinate removed.

At first blush it may seem like the Invariance of domain theorem implies this implementation is not a bijection. However, the appended dimension makes the (forward) image non-open and the theorem does not directly apply.

Properties

dtype

dtype of Tensors transformable by this distribution.

forward_min_event_ndims

Returns the minimal number of dimensions bijector.forward operates on.

graph_parents

Returns this Bijector's graph_parents as a Python list.

inverse_min_event_ndims

Returns the minimal number of dimensions bijector.inverse operates on.

is_constant_jacobian

Returns true iff the Jacobian matrix is not a function of x.

Returns:

  • is_constant_jacobian: Python bool.

name

Returns the string name of this Bijector.

validate_args

Returns True if Tensor arguments will be validated.

Methods

__init__

__init__(
    validate_args=False,
    name='softmax_centered'
)

Constructs Bijector.

A Bijector transforms random variables into new random variables.

Examples:

# Create the Y = g(X) = X transform.
identity = Identity()

# Create the Y = g(X) = exp(X) transform.
exp = Exp()

See Bijector subclass docstring for more details and specific examples.

Args:

  • graph_parents: Python list of graph prerequisites of this Bijector.
  • is_constant_jacobian: Python bool indicating that the Jacobian matrix is not a function of the input.
  • validate_args: Python bool, default False. Whether to validate input with asserts. If validate_args is False, and the inputs are invalid, correct behavior is not guaranteed.
  • dtype: tf.dtype supported by this Bijector. None means dtype is not enforced.
  • forward_min_event_ndims: Python integer indicating the minimum number of dimensions forward operates on.
  • inverse_min_event_ndims: Python integer indicating the minimum number of dimensions inverse operates on. Will be set to forward_min_event_ndims by default, if no value is provided.
  • name: The name to give Ops created by the initializer.

Raises:

  • ValueError: If neither forward_min_event_ndims and inverse_min_event_ndims are specified, or if either of them is negative.
  • ValueError: If a member of graph_parents is not a Tensor.

forward

forward(
    x,
    name='forward'
)

Returns the forward Bijector evaluation, i.e., X = g(Y).

Args:

  • x: Tensor. The input to the "forward" evaluation.
  • name: The name to give this op.

Returns:

Tensor.

Raises:

  • TypeError: if self.dtype is specified and x.dtype is not self.dtype.
  • NotImplementedError: if _forward is not implemented.

forward_event_shape

forward_event_shape(input_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as forward_event_shape_tensor. May be only partially defined.

Args:

  • input_shape: TensorShape indicating event-portion shape passed into forward function.

Returns:

  • forward_event_shape_tensor: TensorShape indicating event-portion shape after applying forward. Possibly unknown.

forward_event_shape_tensor

forward_event_shape_tensor(
    input_shape,
    name='forward_event_shape_tensor'
)

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

Args:

  • input_shape: Tensor, int32 vector indicating event-portion shape passed into forward function.
  • name: name to give to the op

Returns:

  • forward_event_shape_tensor: Tensor, int32 vector indicating event-portion shape after applying forward.

forward_log_det_jacobian

forward_log_det_jacobian(
    x,
    event_ndims,
    name='forward_log_det_jacobian'
)

Returns both the forward_log_det_jacobian.

Args:

  • x: Tensor. The input to the "forward" Jacobian determinant evaluation.
  • event_ndims: Number of dimensions in the probabilistic events being transformed. Must be greater than or equal to self.forward_min_event_ndims. The result is summed over the final dimensions to produce a scalar Jacobian determinant for each event, i.e. it has shape x.shape.ndims - event_ndims dimensions.
  • name: The name to give this op.

Returns:

Tensor, if this bijector is injective. If not injective this is not implemented.

Raises:

  • TypeError: if self.dtype is specified and y.dtype is not self.dtype.
  • NotImplementedError: if neither _forward_log_det_jacobian nor {_inverse, _inverse_log_det_jacobian} are implemented, or this is a non-injective bijector.

inverse

inverse(
    y,
    name='inverse'
)

Returns the inverse Bijector evaluation, i.e., X = g^{-1}(Y).

Args:

  • y: Tensor. The input to the "inverse" evaluation.
  • name: The name to give this op.

Returns:

Tensor, if this bijector is injective. If not injective, returns the k-tuple containing the unique k points (x1, ..., xk) such that g(xi) = y.

Raises:

  • TypeError: if self.dtype is specified and y.dtype is not self.dtype.
  • NotImplementedError: if _inverse is not implemented.

inverse_event_shape

inverse_event_shape(output_shape)

Shape of a single sample from a single batch as a TensorShape.

Same meaning as inverse_event_shape_tensor. May be only partially defined.

Args:

  • output_shape: TensorShape indicating event-portion shape passed into inverse function.

Returns:

  • inverse_event_shape_tensor: TensorShape indicating event-portion shape after applying inverse. Possibly unknown.

inverse_event_shape_tensor

inverse_event_shape_tensor(
    output_shape,
    name='inverse_event_shape_tensor'
)

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

Args:

  • output_shape: Tensor, int32 vector indicating event-portion shape passed into inverse function.
  • name: name to give to the op

Returns:

  • inverse_event_shape_tensor: Tensor, int32 vector indicating event-portion shape after applying inverse.

inverse_log_det_jacobian

inverse_log_det_jacobian(
    y,
    event_ndims,
    name='inverse_log_det_jacobian'
)

Returns the (log o det o Jacobian o inverse)(y).

Mathematically, returns: log(det(dX/dY))(Y). (Recall that: X=g^{-1}(Y).)

Note that forward_log_det_jacobian is the negative of this function, evaluated at g^{-1}(y).

Args:

  • y: Tensor. The input to the "inverse" Jacobian determinant evaluation.
  • event_ndims: Number of dimensions in the probabilistic events being transformed. Must be greater than or equal to self.inverse_min_event_ndims. The result is summed over the final dimensions to produce a scalar Jacobian determinant for each event, i.e. it has shape y.shape.ndims - event_ndims dimensions.
  • name: The name to give this op.

Returns:

Tensor, if this bijector is injective. If not injective, returns the tuple of local log det Jacobians, log(det(Dg_i^{-1}(y))), where g_i is the restriction of g to the ith partition Di.

Raises:

  • TypeError: if self.dtype is specified and y.dtype is not self.dtype.
  • NotImplementedError: if _inverse_log_det_jacobian is not implemented.