TF 2.0 is out! Get hands-on practice at TF World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tfp.bijectors.Affine

View source on GitHub

Class Affine

Compute Y = g(X; shift, scale) = scale @ X + shift.

Inherits From: Bijector

Here scale = c * I + diag(D1) + tril(L) + V @ diag(D2) @ V.T.

In TF parlance, the scale term is logically equivalent to:

scale = (
  scale_identity_multiplier * tf.diag(tf.ones(d)) +
  tf.diag(scale_diag) +
  scale_tril +
  scale_perturb_factor @ diag(scale_perturb_diag) @
    tf.transpose([scale_perturb_factor])
)

The scale term is applied without necessarily materializing constituent matrices, i.e., the matmul is matrix-free when possible.

Examples

# Y = X
b = Affine()

# Y = X + shift
b = Affine(shift=[1., 2, 3])

# Y = 2 * I @ X.T + shift
b = Affine(shift=[1., 2, 3],
           scale_identity_multiplier=2.)

# Y = tf.diag(d1) @ X.T + shift
b = Affine(shift=[1., 2, 3],
           scale_diag=[-1., 2, 1])         # Implicitly 3x3.

# Y = (I + v * v.T) @ X.T + shift
b = Affine(shift=[1., 2, 3],
           scale_perturb_factor=[[1., 0],
                                 [0, 1],
                                 [1, 1]])

# Y = (diag(d1) + v * diag(d2) * v.T) @ X.T + shift
b = Affine(shift=[1., 2, 3],
           scale_diag=[1., 3, 3],          # Implicitly 3x3.
           scale_perturb_diag=[2., 1],     # Implicitly 2x2.
           scale_perturb_factor=[[1., 0],
                                 [0, 1],
                                 [1, 1]])

__init__

View source

__init__(
    shift=None,
    scale_identity_multiplier=None,
    scale_diag=None,
    scale_tril=None,
    scale_perturb_factor=None,
    scale_perturb_diag=None,
    adjoint=False,
    validate_args=False,
    name='affine',
    dtype=None
)

Instantiates the Affine bijector.

This Bijector is initialized with shift Tensor and scale arguments, giving the forward operation:

Y = g(X) = scale @ X + shift

where the scale term is logically equivalent to:

scale = (
  scale_identity_multiplier * tf.diag(tf.ones(d)) +
  tf.diag(scale_diag) +
  scale_tril +
  scale_perturb_factor @ diag(scale_perturb_diag) @
    tf.transpose([scale_perturb_factor])
)

If none of scale_identity_multiplier, scale_diag, or scale_tril are specified then scale += IdentityMatrix. Otherwise specifying a scale argument has the semantics of scale += Expand(arg), i.e., scale_diag != None means scale += tf.diag(scale_diag).

Args:

  • shift: Floating-point Tensor. If this is set to None, no shift is applied.
  • scale_identity_multiplier: floating point rank 0 Tensor representing a scaling done to the identity matrix. When scale_identity_multiplier = scale_diag = scale_tril = None then scale += IdentityMatrix. Otherwise no scaled-identity-matrix is added to scale.
  • scale_diag: Floating-point Tensor representing the diagonal matrix. scale_diag has shape [N1, N2, ... k], which represents a k x k diagonal matrix. When None no diagonal term is added to scale.
  • scale_tril: Floating-point Tensor representing the lower triangular matrix. scale_tril has shape [N1, N2, ... k, k], which represents a k x k lower triangular matrix. When None no scale_tril term is added to scale. The upper triangular elements above the diagonal are ignored.
  • scale_perturb_factor: Floating-point Tensor representing factor matrix with last two dimensions of shape (k, r). When None, no rank-r update is added to scale.
  • scale_perturb_diag: Floating-point Tensor representing the diagonal matrix. scale_perturb_diag has shape [N1, N2, ... r], which represents an r x r diagonal matrix. When None low rank updates will take the form scale_perturb_factor * scale_perturb_factor.T.
  • adjoint: Python bool indicating whether to use the scale matrix as specified or its adjoint. Default value: False.
  • validate_args: Python bool indicating whether arguments should be checked for correctness.
  • name: Python str name given to ops managed by this object.
  • dtype: tf.DType to prefer when converting args to Tensors. Else, we fall back to a common dtype inferred from the args, finally falling back to float32.

Raises:

  • ValueError: if perturb_diag is specified but not perturb_factor.
  • TypeError: if shift has different dtype from scale arguments.

Properties

adjoint

bool indicating scale should be used as conjugate transpose.

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.

name_scope

Returns a tf.name_scope instance for this class.

scale

The scale LinearOperator in Y = scale @ X + shift.

shift

The shift Tensor in Y = scale @ X + shift.

submodules

Sequence of all sub-modules.

Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

a = tf.Module()
b = tf.Module()
c = tf.Module()
a.b = b
b.c = c
assert list(a.submodules) == [b, c]
assert list(b.submodules) == [c]
assert list(c.submodules) == []

Returns:

A sequence of all submodules.

trainable_variables

Sequence of variables owned by this module and it's submodules.

Returns:

A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).

validate_args

Returns True if Tensor arguments will be validated.

variables

Sequence of variables owned by this module and it's submodules.

Returns:

A sequence of variables for the current module (sorted by attribute name) followed by variables from all submodules recursively (breadth first).

Methods

__call__

View source

__call__(
    value,
    name=None,
    **kwargs
)

Applies or composes the Bijector, depending on input type.

This is a convenience function which applies the Bijector instance in three different ways, depending on the input:

  1. If the input is a tfd.Distribution instance, return tfd.TransformedDistribution(distribution=input, bijector=self).
  2. If the input is a tfb.Bijector instance, return tfb.Chain([self, input]).
  3. Otherwise, return self.forward(input)

Args:

  • value: A tfd.Distribution, tfb.Bijector, or a Tensor.
  • name: Python str name given to ops created by this function.
  • **kwargs: Additional keyword arguments passed into the created tfd.TransformedDistribution, tfb.Bijector, or self.forward.

Returns:

  • composition: A tfd.TransformedDistribution if the input was a tfd.Distribution, a tfb.Chain if the input was a tfb.Bijector, or a Tensor computed by self.forward.

Examples

sigmoid = tfb.Reciprocal()(
    tfb.AffineScalar(shift=1.)(
      tfb.Exp()(
        tfb.AffineScalar(scale=-1.))))
# ==> `tfb.Chain([
#         tfb.Reciprocal(),
#         tfb.AffineScalar(shift=1.),
#         tfb.Exp(),
#         tfb.AffineScalar(scale=-1.),
#      ])`  # ie, `tfb.Sigmoid()`

log_normal = tfb.Exp()(tfd.Normal(0, 1))
# ==> `tfd.TransformedDistribution(tfd.Normal(0, 1), tfb.Exp())`

tfb.Exp()([-1., 0., 1.])
# ==> tf.exp([-1., 0., 1.])

forward

View source

forward(
    x,
    name='forward',
    **kwargs
)

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.
  • **kwargs: Named arguments forwarded to subclass implementation.

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

View source

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

View source

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

View source

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

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 rank(x) - event_ndims dimensions.
  • name: The name to give this op.
  • **kwargs: Named arguments forwarded to subclass implementation.

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

View source

inverse(
    y,
    name='inverse',
    **kwargs
)

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.
  • **kwargs: Named arguments forwarded to subclass implementation.

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

View source

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

View source

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

View source

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

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 rank(y) - event_ndims dimensions.
  • name: The name to give this op.
  • **kwargs: Named arguments forwarded to subclass implementation.

Returns:

  • ildj: 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.

with_name_scope

with_name_scope(
    cls,
    method
)

Decorator to automatically enter the module name scope.

class MyModule(tf.Module):
  @tf.Module.with_name_scope
  def __call__(self, x):
    if not hasattr(self, 'w'):
      self.w = tf.Variable(tf.random.normal([x.shape[1], 64]))
    return tf.matmul(x, self.w)

Using the above module would produce tf.Variables and tf.Tensors whose names included the module name:

mod = MyModule()
mod(tf.ones([8, 32]))
# ==> <tf.Tensor: ...>
mod.w
# ==> <tf.Variable ...'my_module/w:0'>

Args:

  • method: The method to wrap.

Returns:

The original method wrapped such that it enters the module's name scope.