def __init__(self,
loc=None,
scale=None,
validate_args=False,
allow_nan_stats=True,
name="VectorExponentialLinearOperator"):
"""Construct Vector Exponential distribution supported on a subset of `R^k`.
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this.
Recall that `covariance = scale @ scale.T`.
Additional leading dimensions (if any) will index batches.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale: Instance of `LinearOperator` with same `dtype` as `loc` and shape
`[B1, ..., Bb, k, k]`.
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.
allow_nan_stats: Python `bool`, default `True`. If `False`, raise an
exception if a statistic (e.g. mean/mode/etc...) is undefined for any
batch member If `True`, batch members with valid parameters leading to
undefined statistics will return NaN for this statistic.
name: The name to give Ops created by the initializer.
Raises:
ValueError: if `scale` is unspecified.
TypeError: if not `scale.dtype.is_floating`
"""
parameters = distribution_util.parent_frame_arguments()
if scale is None:
raise ValueError("Missing required `scale` parameter.")
if not scale.dtype.is_floating:
raise TypeError("`scale` parameter must have floating-point dtype.")
with ops.name_scope(name, values=[loc] + scale.graph_parents) as name:
# Since expand_dims doesn't preserve constant-ness, we obtain the
# non-dynamic value if possible.
loc = ops.convert_to_tensor(loc, name="loc") if loc is not None else loc
batch_shape, event_shape = distribution_util.shapes_from_loc_and_scale(
loc, scale)
super(VectorExponentialLinearOperator, self).__init__(
distribution=exponential.Exponential(rate=array_ops.ones(
[], dtype=scale.dtype), allow_nan_stats=allow_nan_stats),
bijector=bijectors.AffineLinearOperator(
shift=loc, scale=scale, validate_args=validate_args),
batch_shape=batch_shape,
event_shape=event_shape,
validate_args=validate_args,
name=name)
self._parameters = parameters
def __init__(self,
df,
scale,
cholesky_input_output_matrices=False,
validate_args=False,
allow_nan_stats=True,
name="WishartCholesky"):
"""Construct Wishart distributions.
Args:
df: `float` or `double` `Tensor`. Degrees of freedom, must be greater than
or equal to dimension of the scale matrix.
scale: `float` or `double` `Tensor`. The Cholesky factorization of
the symmetric positive definite scale matrix of the distribution.
cholesky_input_output_matrices: Python `bool`. Any function which whose
input or output is a matrix assumes the input is Cholesky and returns a
Cholesky factored matrix. Example `log_prob` input takes a Cholesky and
`sample_n` returns a Cholesky when
`cholesky_input_output_matrices=True`.
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.
name: Python `str` name prefixed to Ops created by this class.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name, values=[scale]) as name:
with ops.name_scope("init", values=[scale]):
scale = ops.convert_to_tensor(scale)
if validate_args:
scale = control_flow_ops.with_dependencies([
check_ops.assert_positive(
array_ops.matrix_diag_part(scale),
message="scale must be positive definite"),
check_ops.assert_equal(
array_ops.shape(scale)[-1],
array_ops.shape(scale)[-2],
message="scale must be square")
] if validate_args else [], scale)
super(WishartCholesky, self).__init__(
df=df,
scale_operator=linalg.LinearOperatorLowerTriangular(
tril=scale,
is_non_singular=True,
is_positive_definite=True,
is_square=True),
cholesky_input_output_matrices=cholesky_input_output_matrices,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters
def __init__(self,
df,
scale,
cholesky_input_output_matrices=False,
validate_args=False,
allow_nan_stats=True,
name="WishartCholesky"):
"""Construct Wishart distributions.
Args:
df: `float` or `double` `Tensor`. Degrees of freedom, must be greater than
or equal to dimension of the scale matrix.
scale: `float` or `double` `Tensor`. The Cholesky factorization of
the symmetric positive definite scale matrix of the distribution.
cholesky_input_output_matrices: Python `bool`. Any function which whose
input or output is a matrix assumes the input is Cholesky and returns a
Cholesky factored matrix. Example `log_prob` input takes a Cholesky and
`sample_n` returns a Cholesky when
`cholesky_input_output_matrices=True`.
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.
name: Python `str` name prefixed to Ops created by this class.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name, values=[scale]) as name:
with ops.name_scope("init", values=[scale]):
scale = ops.convert_to_tensor(scale)
if validate_args:
scale = control_flow_ops.with_dependencies([
check_ops.assert_positive(
array_ops.matrix_diag_part(scale),
message="scale must be positive definite"),
check_ops.assert_equal(array_ops.shape(scale)[-1],
array_ops.shape(scale)[-2],
message="scale must be square")
] if validate_args else [], scale)
super(WishartCholesky, self).__init__(
df=df,
scale_operator=linalg.LinearOperatorLowerTriangular(
tril=scale,
is_non_singular=True,
is_positive_definite=True,
is_square=True),
cholesky_input_output_matrices=cholesky_input_output_matrices,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters
def __init__(self,
loc,
scale_diag,
validate_args=False,
allow_nan_stats=True,
name="MultivariateNormalDiagWithSoftplusScale"):
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name, values=[scale_diag]) as name:
super(MultivariateNormalDiagWithSoftplusScale, self).__init__(
loc=loc,
scale_diag=nn.softplus(scale_diag),
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters
def __init__(self,
loc,
scale,
skewness=None,
tailweight=None,
distribution=None,
validate_args=False,
allow_nan_stats=True,
name="SinhArcsinh"):
"""Construct SinhArcsinh distribution on `(-inf, inf)`.
Arguments `(loc, scale, skewness, tailweight)` must have broadcastable shape
(indexing batch dimensions). They must all have the same `dtype`.
Args:
loc: Floating-point `Tensor`.
scale: `Tensor` of same `dtype` as `loc`.
skewness: Skewness parameter. Default is `0.0` (no skew).
tailweight: Tailweight parameter. Default is `1.0` (unchanged tailweight)
distribution: `tf.Distribution`-like instance. Distribution that is
transformed to produce this distribution.
Default is `tf.distributions.Normal(0., 1.)`.
Must be a scalar-batch, scalar-event distribution. Typically
`distribution.reparameterization_type = FULLY_REPARAMETERIZED` or it is
a function of non-trainable parameters. WARNING: If you backprop through
a `SinhArcsinh` sample and `distribution` is not
`FULLY_REPARAMETERIZED` yet is a function of trainable variables, then
the gradient will be incorrect!
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.
name: Python `str` name prefixed to Ops created by this class.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name,
values=[loc, scale, skewness, tailweight]) as name:
loc = ops.convert_to_tensor(loc, name="loc")
dtype = loc.dtype
scale = ops.convert_to_tensor(scale, name="scale", dtype=dtype)
tailweight = 1. if tailweight is None else tailweight
has_default_skewness = skewness is None
skewness = 0. if skewness is None else skewness
tailweight = ops.convert_to_tensor(
tailweight, name="tailweight", dtype=dtype)
skewness = ops.convert_to_tensor(skewness, name="skewness", dtype=dtype)
batch_shape = distribution_util.get_broadcast_shape(
loc, scale, tailweight, skewness)
# Recall, with Z a random variable,
# Y := loc + C * F(Z),
# F(Z) := Sinh( (Arcsinh(Z) + skewness) * tailweight )
# F_0(Z) := Sinh( Arcsinh(Z) * tailweight )
# C := 2 * scale / F_0(2)
if distribution is None:
distribution = normal.Normal(
loc=array_ops.zeros([], dtype=dtype),
scale=array_ops.ones([], dtype=dtype),
allow_nan_stats=allow_nan_stats)
else:
asserts = distribution_util.maybe_check_scalar_distribution(
distribution, dtype, validate_args)
if asserts:
loc = control_flow_ops.with_dependencies(asserts, loc)
# Make the SAS bijector, 'F'.
f = bijectors.SinhArcsinh(
skewness=skewness, tailweight=tailweight)
if has_default_skewness:
f_noskew = f
else:
f_noskew = bijectors.SinhArcsinh(
skewness=skewness.dtype.as_numpy_dtype(0.),
tailweight=tailweight)
# Make the AffineScalar bijector, Z --> loc + scale * Z (2 / F_0(2))
c = 2 * scale / f_noskew.forward(ops.convert_to_tensor(2, dtype=dtype))
affine = bijectors.AffineScalar(
shift=loc,
scale=c,
validate_args=validate_args)
bijector = bijectors.Chain([affine, f])
super(SinhArcsinh, self).__init__(
distribution=distribution,
bijector=bijector,
batch_shape=batch_shape,
validate_args=validate_args,
name=name)
self._parameters = parameters
self._loc = loc
self._scale = scale
self._tailweight = tailweight
self._skewness = skewness
def __init__(self,
loc=None,
scale=None,
validate_args=False,
allow_nan_stats=True,
name="VectorLaplaceLinearOperator"):
"""Construct Vector Laplace distribution on `R^k`.
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this.
Recall that `covariance = 2 * scale @ scale.T`.
Additional leading dimensions (if any) will index batches.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale: Instance of `LinearOperator` with same `dtype` as `loc` and shape
`[B1, ..., Bb, k, k]`.
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.
allow_nan_stats: Python `bool`, default `True`. If `False`, raise an
exception if a statistic (e.g. mean/mode/etc...) is undefined for any
batch member If `True`, batch members with valid parameters leading to
undefined statistics will return NaN for this statistic.
name: The name to give Ops created by the initializer.
Raises:
ValueError: if `scale` is unspecified.
TypeError: if not `scale.dtype.is_floating`
"""
parameters = distribution_util.parent_frame_arguments()
if scale is None:
raise ValueError("Missing required `scale` parameter.")
if not scale.dtype.is_floating:
raise TypeError(
"`scale` parameter must have floating-point dtype.")
with ops.name_scope(name, values=[loc] + scale.graph_parents):
# Since expand_dims doesn't preserve constant-ness, we obtain the
# non-dynamic value if possible.
loc = ops.convert_to_tensor(loc,
name="loc") if loc is not None else loc
batch_shape, event_shape = distribution_util.shapes_from_loc_and_scale(
loc, scale)
super(VectorLaplaceLinearOperator,
self).__init__(distribution=laplace.Laplace(
loc=array_ops.zeros([], dtype=scale.dtype),
scale=array_ops.ones([], dtype=scale.dtype)),
bijector=bijectors.AffineLinearOperator(
shift=loc,
scale=scale,
validate_args=validate_args),
batch_shape=batch_shape,
event_shape=event_shape,
validate_args=validate_args,
name=name)
self._parameters = parameters
def __init__(self,
loc=None,
scale_diag=None,
scale_identity_multiplier=None,
validate_args=False,
allow_nan_stats=True,
name="VectorLaplaceDiag"):
"""Construct Vector Laplace distribution on `R^k`.
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this.
Recall that `covariance = 2 * scale @ scale.T`.
```none
scale = diag(scale_diag + scale_identity_multiplier * ones(k))
```
where:
* `scale_diag.shape = [k]`, and,
* `scale_identity_multiplier.shape = []`.
Additional leading dimensions (if any) will index batches.
If both `scale_diag` and `scale_identity_multiplier` are `None`, then
`scale` is the Identity matrix.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale_diag: Non-zero, floating-point `Tensor` representing a diagonal
matrix added to `scale`. May have shape `[B1, ..., Bb, k]`, `b >= 0`,
and characterizes `b`-batches of `k x k` diagonal matrices added to
`scale`. When both `scale_identity_multiplier` and `scale_diag` are
`None` then `scale` is the `Identity`.
scale_identity_multiplier: Non-zero, floating-point `Tensor` representing
a scaled-identity-matrix added to `scale`. May have shape
`[B1, ..., Bb]`, `b >= 0`, and characterizes `b`-batches of scaled
`k x k` identity matrices added to `scale`. When both
`scale_identity_multiplier` and `scale_diag` are `None` then `scale` is
the `Identity`.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
ValueError: if at most `scale_identity_multiplier` is specified.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name):
with ops.name_scope("init", values=[
loc, scale_diag, scale_identity_multiplier]):
# No need to validate_args while making diag_scale. The returned
# LinearOperatorDiag has an assert_non_singular method that is called by
# the Bijector.
scale = distribution_util.make_diag_scale(
loc=loc,
scale_diag=scale_diag,
scale_identity_multiplier=scale_identity_multiplier,
validate_args=False,
assert_positive=False)
super(VectorLaplaceDiag, self).__init__(
loc=loc,
scale=scale,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters
def __init__(self,
df,
loc=None,
scale_identity_multiplier=None,
scale_diag=None,
scale_tril=None,
scale_perturb_factor=None,
scale_perturb_diag=None,
validate_args=False,
allow_nan_stats=True,
name="VectorStudentT"):
"""Instantiates the vector Student's t-distributions on `R^k`.
The `batch_shape` is the broadcast between `df.batch_shape` and
`Affine.batch_shape` where `Affine` is constructed from `loc` and
`scale_*` arguments.
The `event_shape` is the event shape of `Affine.event_shape`.
Args:
df: Floating-point `Tensor`. The degrees of freedom of the
distribution(s). `df` must contain only positive values. Must be
scalar if `loc`, `scale_*` imply non-scalar batch_shape or must have the
same `batch_shape` implied by `loc`, `scale_*`.
loc: Floating-point `Tensor`. If this is set to `None`, no `loc` 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 diagonal matrix.
`scale_diag` 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`.
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.
name: Python `str` name prefixed to Ops created by this class.
"""
parameters = distribution_util.parent_frame_arguments()
graph_parents = [df, loc, scale_identity_multiplier, scale_diag,
scale_tril, scale_perturb_factor, scale_perturb_diag]
with ops.name_scope(name) as name:
with ops.name_scope("init", values=graph_parents):
# The shape of the _VectorStudentT distribution is governed by the
# relationship between df.batch_shape and affine.batch_shape. In
# pseudocode the basic procedure is:
# if df.batch_shape is scalar:
# if affine.batch_shape is not scalar:
# # broadcast distribution.sample so
# # it has affine.batch_shape.
# self.batch_shape = affine.batch_shape
# else:
# if affine.batch_shape is scalar:
# # let affine broadcasting do its thing.
# self.batch_shape = df.batch_shape
# All of the above magic is actually handled by TransformedDistribution.
# Here we really only need to collect the affine.batch_shape and decide
# what we're going to pass in to TransformedDistribution's
# (override) batch_shape arg.
affine = bijectors.Affine(
shift=loc,
scale_identity_multiplier=scale_identity_multiplier,
scale_diag=scale_diag,
scale_tril=scale_tril,
scale_perturb_factor=scale_perturb_factor,
scale_perturb_diag=scale_perturb_diag,
validate_args=validate_args)
distribution = student_t.StudentT(
df=df,
loc=array_ops.zeros([], dtype=affine.dtype),
scale=array_ops.ones([], dtype=affine.dtype))
batch_shape, override_event_shape = (
distribution_util.shapes_from_loc_and_scale(
affine.shift, affine.scale))
override_batch_shape = distribution_util.pick_vector(
distribution.is_scalar_batch(),
batch_shape,
constant_op.constant([], dtype=dtypes.int32))
super(_VectorStudentT, self).__init__(
distribution=distribution,
bijector=affine,
batch_shape=override_batch_shape,
event_shape=override_event_shape,
validate_args=validate_args,
name=name)
self._parameters = parameters
def __init__(self,
loc=None,
scale_diag=None,
scale_identity_multiplier=None,
skewness=None,
tailweight=None,
distribution=None,
validate_args=False,
allow_nan_stats=True,
name="MultivariateNormalLinearOperator"):
"""Construct VectorSinhArcsinhDiag distribution on `R^k`.
The arguments `scale_diag` and `scale_identity_multiplier` combine to
define the diagonal `scale` referred to in this class docstring:
```none
scale = diag(scale_diag + scale_identity_multiplier * ones(k))
```
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this
Additional leading dimensions (if any) will index batches.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale_diag: Non-zero, floating-point `Tensor` representing a diagonal
matrix added to `scale`. May have shape `[B1, ..., Bb, k]`, `b >= 0`,
and characterizes `b`-batches of `k x k` diagonal matrices added to
`scale`. When both `scale_identity_multiplier` and `scale_diag` are
`None` then `scale` is the `Identity`.
scale_identity_multiplier: Non-zero, floating-point `Tensor` representing
a scale-identity-matrix added to `scale`. May have shape
`[B1, ..., Bb]`, `b >= 0`, and characterizes `b`-batches of scale
`k x k` identity matrices added to `scale`. When both
`scale_identity_multiplier` and `scale_diag` are `None` then `scale`
is the `Identity`.
skewness: Skewness parameter. floating-point `Tensor` with shape
broadcastable with `event_shape`.
tailweight: Tailweight parameter. floating-point `Tensor` with shape
broadcastable with `event_shape`.
distribution: `tf.Distribution`-like instance. Distribution from which `k`
iid samples are used as input to transformation `F`. Default is
`tf.distributions.Normal(loc=0., scale=1.)`.
Must be a scalar-batch, scalar-event distribution. Typically
`distribution.reparameterization_type = FULLY_REPARAMETERIZED` or it is
a function of non-trainable parameters. WARNING: If you backprop through
a VectorSinhArcsinhDiag sample and `distribution` is not
`FULLY_REPARAMETERIZED` yet is a function of trainable variables, then
the gradient will be incorrect!
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
ValueError: if at most `scale_identity_multiplier` is specified.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(
name,
values=[
loc, scale_diag, scale_identity_multiplier, skewness, tailweight
]) as name:
loc = ops.convert_to_tensor(loc, name="loc") if loc is not None else loc
tailweight = 1. if tailweight is None else tailweight
has_default_skewness = skewness is None
skewness = 0. if skewness is None else skewness
# Recall, with Z a random variable,
# Y := loc + C * F(Z),
# F(Z) := Sinh( (Arcsinh(Z) + skewness) * tailweight )
# F_0(Z) := Sinh( Arcsinh(Z) * tailweight )
# C := 2 * scale / F_0(2)
# Construct shapes and 'scale' out of the scale_* and loc kwargs.
# scale_linop is only an intermediary to:
# 1. get shapes from looking at loc and the two scale args.
# 2. combine scale_diag with scale_identity_multiplier, which gives us
# 'scale', which in turn gives us 'C'.
scale_linop = distribution_util.make_diag_scale(
loc=loc,
scale_diag=scale_diag,
scale_identity_multiplier=scale_identity_multiplier,
validate_args=False,
assert_positive=False)
batch_shape, event_shape = distribution_util.shapes_from_loc_and_scale(
loc, scale_linop)
# scale_linop.diag_part() is efficient since it is a diag type linop.
scale_diag_part = scale_linop.diag_part()
dtype = scale_diag_part.dtype
if distribution is None:
distribution = normal.Normal(
loc=array_ops.zeros([], dtype=dtype),
scale=array_ops.ones([], dtype=dtype),
allow_nan_stats=allow_nan_stats)
else:
asserts = distribution_util.maybe_check_scalar_distribution(
distribution, dtype, validate_args)
if asserts:
scale_diag_part = control_flow_ops.with_dependencies(
asserts, scale_diag_part)
# Make the SAS bijector, 'F'.
skewness = ops.convert_to_tensor(skewness, dtype=dtype, name="skewness")
tailweight = ops.convert_to_tensor(
tailweight, dtype=dtype, name="tailweight")
f = bijectors.SinhArcsinh(
skewness=skewness, tailweight=tailweight)
if has_default_skewness:
f_noskew = f
else:
f_noskew = bijectors.SinhArcsinh(
skewness=skewness.dtype.as_numpy_dtype(0.),
tailweight=tailweight)
# Make the Affine bijector, Z --> loc + C * Z.
c = 2 * scale_diag_part / f_noskew.forward(
ops.convert_to_tensor(2, dtype=dtype))
affine = bijectors.Affine(
shift=loc, scale_diag=c, validate_args=validate_args)
bijector = bijectors.Chain([affine, f])
super(VectorSinhArcsinhDiag, self).__init__(
distribution=distribution,
bijector=bijector,
batch_shape=batch_shape,
event_shape=event_shape,
validate_args=validate_args,
name=name)
self._parameters = parameters
self._loc = loc
self._scale = scale_linop
self._tailweight = tailweight
self._skewness = skewness
def __init__(self,
loc,
scale,
quadrature_size=8,
quadrature_fn=quadrature_scheme_lognormal_quantiles,
validate_args=False,
allow_nan_stats=True,
name="PoissonLogNormalQuadratureCompound"):
"""Constructs the PoissonLogNormalQuadratureCompound`.
Note: `probs` returned by (optional) `quadrature_fn` are presumed to be
either a length-`quadrature_size` vector or a batch of vectors in 1-to-1
correspondence with the returned `grid`. (I.e., broadcasting is only
partially supported.)
Args:
loc: `float`-like (batch of) scalar `Tensor`; the location parameter of
the LogNormal prior.
scale: `float`-like (batch of) scalar `Tensor`; the scale parameter of
the LogNormal prior.
quadrature_size: Python `int` scalar representing the number of quadrature
points.
quadrature_fn: Python callable taking `loc`, `scale`,
`quadrature_size`, `validate_args` and returning `tuple(grid, probs)`
representing the LogNormal grid and corresponding normalized weight.
normalized) weight.
Default value: `quadrature_scheme_lognormal_quantiles`.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
TypeError: if `quadrature_grid` and `quadrature_probs` have different base
`dtype`.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name, values=[loc, scale]) as name:
if loc is not None:
loc = ops.convert_to_tensor(loc, name="loc")
if scale is not None:
scale = ops.convert_to_tensor(
scale, dtype=None if loc is None else loc.dtype, name="scale")
self._quadrature_grid, self._quadrature_probs = tuple(quadrature_fn(
loc, scale, quadrature_size, validate_args))
dt = self._quadrature_grid.dtype
if dt.base_dtype != self._quadrature_probs.dtype.base_dtype:
raise TypeError("Quadrature grid dtype ({}) does not match quadrature "
"probs dtype ({}).".format(
dt.name, self._quadrature_probs.dtype.name))
self._distribution = poisson_lib.Poisson(
log_rate=self._quadrature_grid,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats)
self._mixture_distribution = categorical_lib.Categorical(
logits=math_ops.log(self._quadrature_probs),
validate_args=validate_args,
allow_nan_stats=allow_nan_stats)
self._loc = loc
self._scale = scale
self._quadrature_size = quadrature_size
super(PoissonLogNormalQuadratureCompound, self).__init__(
dtype=dt,
reparameterization_type=distribution_lib.NOT_REPARAMETERIZED,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
parameters=parameters,
graph_parents=[loc, scale],
name=name)
def __init__(self,
loc,
scale,
skewness=None,
tailweight=None,
distribution=None,
validate_args=False,
allow_nan_stats=True,
name="SinhArcsinh"):
"""Construct SinhArcsinh distribution on `(-inf, inf)`.
Arguments `(loc, scale, skewness, tailweight)` must have broadcastable shape
(indexing batch dimensions). They must all have the same `dtype`.
Args:
loc: Floating-point `Tensor`.
scale: `Tensor` of same `dtype` as `loc`.
skewness: Skewness parameter. Default is `0.0` (no skew).
tailweight: Tailweight parameter. Default is `1.0` (unchanged tailweight)
distribution: `tf.Distribution`-like instance. Distribution that is
transformed to produce this distribution.
Default is `tf.distributions.Normal(0., 1.)`.
Must be a scalar-batch, scalar-event distribution. Typically
`distribution.reparameterization_type = FULLY_REPARAMETERIZED` or it is
a function of non-trainable parameters. WARNING: If you backprop through
a `SinhArcsinh` sample and `distribution` is not
`FULLY_REPARAMETERIZED` yet is a function of trainable variables, then
the gradient will be incorrect!
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.
name: Python `str` name prefixed to Ops created by this class.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name, values=[loc, scale, skewness,
tailweight]) as name:
loc = ops.convert_to_tensor(loc, name="loc")
dtype = loc.dtype
scale = ops.convert_to_tensor(scale, name="scale", dtype=dtype)
tailweight = 1. if tailweight is None else tailweight
has_default_skewness = skewness is None
skewness = 0. if skewness is None else skewness
tailweight = ops.convert_to_tensor(tailweight,
name="tailweight",
dtype=dtype)
skewness = ops.convert_to_tensor(skewness,
name="skewness",
dtype=dtype)
batch_shape = distribution_util.get_broadcast_shape(
loc, scale, tailweight, skewness)
# Recall, with Z a random variable,
# Y := loc + C * F(Z),
# F(Z) := Sinh( (Arcsinh(Z) + skewness) * tailweight )
# F_0(Z) := Sinh( Arcsinh(Z) * tailweight )
# C := 2 * scale / F_0(2)
if distribution is None:
distribution = normal.Normal(loc=array_ops.zeros([],
dtype=dtype),
scale=array_ops.ones([],
dtype=dtype),
allow_nan_stats=allow_nan_stats)
else:
asserts = distribution_util.maybe_check_scalar_distribution(
distribution, dtype, validate_args)
if asserts:
loc = control_flow_ops.with_dependencies(asserts, loc)
# Make the SAS bijector, 'F'.
f = bijectors.SinhArcsinh(skewness=skewness, tailweight=tailweight)
if has_default_skewness:
f_noskew = f
else:
f_noskew = bijectors.SinhArcsinh(
skewness=skewness.dtype.as_numpy_dtype(0.),
tailweight=tailweight)
# Make the AffineScalar bijector, Z --> loc + scale * Z (2 / F_0(2))
c = 2 * scale / f_noskew.forward(
ops.convert_to_tensor(2, dtype=dtype))
affine = bijectors.AffineScalar(shift=loc,
scale=c,
validate_args=validate_args)
bijector = bijectors.Chain([affine, f])
super(SinhArcsinh, self).__init__(distribution=distribution,
bijector=bijector,
batch_shape=batch_shape,
validate_args=validate_args,
name=name)
self._parameters = parameters
self._loc = loc
self._scale = scale
self._tailweight = tailweight
self._skewness = skewness
def __init__(self,
loc=None,
scale_diag=None,
scale_identity_multiplier=None,
validate_args=False,
allow_nan_stats=True,
name="VectorLaplaceDiag"):
"""Construct Vector Laplace distribution on `R^k`.
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this.
Recall that `covariance = 2 * scale @ scale.T`.
```none
scale = diag(scale_diag + scale_identity_multiplier * ones(k))
```
where:
* `scale_diag.shape = [k]`, and,
* `scale_identity_multiplier.shape = []`.
Additional leading dimensions (if any) will index batches.
If both `scale_diag` and `scale_identity_multiplier` are `None`, then
`scale` is the Identity matrix.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale_diag: Non-zero, floating-point `Tensor` representing a diagonal
matrix added to `scale`. May have shape `[B1, ..., Bb, k]`, `b >= 0`,
and characterizes `b`-batches of `k x k` diagonal matrices added to
`scale`. When both `scale_identity_multiplier` and `scale_diag` are
`None` then `scale` is the `Identity`.
scale_identity_multiplier: Non-zero, floating-point `Tensor` representing
a scaled-identity-matrix added to `scale`. May have shape
`[B1, ..., Bb]`, `b >= 0`, and characterizes `b`-batches of scaled
`k x k` identity matrices added to `scale`. When both
`scale_identity_multiplier` and `scale_diag` are `None` then `scale` is
the `Identity`.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
ValueError: if at most `scale_identity_multiplier` is specified.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name):
with ops.name_scope("init",
values=[
loc, scale_diag, scale_identity_multiplier
]):
# No need to validate_args while making diag_scale. The returned
# LinearOperatorDiag has an assert_non_singular method that is called by
# the Bijector.
scale = distribution_util.make_diag_scale(
loc=loc,
scale_diag=scale_diag,
scale_identity_multiplier=scale_identity_multiplier,
validate_args=False,
assert_positive=False)
super(VectorLaplaceDiag,
self).__init__(loc=loc,
scale=scale,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters
def __init__(self,
mix_loc,
temperature,
distribution,
loc=None,
scale=None,
quadrature_size=8,
quadrature_fn=quadrature_scheme_softmaxnormal_quantiles,
validate_args=False,
allow_nan_stats=True,
name="VectorDiffeomixture"):
"""Constructs the VectorDiffeomixture on `R^d`.
The vector diffeomixture (VDM) approximates the compound distribution
```none
p(x) = int p(x | z) p(z) dz,
where z is in the K-simplex, and
p(x | z) := p(x | loc=sum_k z[k] loc[k], scale=sum_k z[k] scale[k])
```
Args:
mix_loc: `float`-like `Tensor` with shape `[b1, ..., bB, K-1]`.
In terms of samples, larger `mix_loc[..., k]` ==>
`Z` is more likely to put more weight on its `kth` component.
temperature: `float`-like `Tensor`. Broadcastable with `mix_loc`.
In terms of samples, smaller `temperature` means one component is more
likely to dominate. I.e., smaller `temperature` makes the VDM look more
like a standard mixture of `K` components.
distribution: `tf.Distribution`-like instance. Distribution from which `d`
iid samples are used as input to the selected affine transformation.
Must be a scalar-batch, scalar-event distribution. Typically
`distribution.reparameterization_type = FULLY_REPARAMETERIZED` or it is
a function of non-trainable parameters. WARNING: If you backprop through
a VectorDiffeomixture sample and the `distribution` is not
`FULLY_REPARAMETERIZED` yet is a function of trainable variables, then
the gradient will be incorrect!
loc: Length-`K` list of `float`-type `Tensor`s. The `k`-th element
represents the `shift` used for the `k`-th affine transformation. If
the `k`-th item is `None`, `loc` is implicitly `0`. When specified,
must have shape `[B1, ..., Bb, d]` where `b >= 0` and `d` is the event
size.
scale: Length-`K` list of `LinearOperator`s. Each should be
positive-definite and operate on a `d`-dimensional vector space. The
`k`-th element represents the `scale` used for the `k`-th affine
transformation. `LinearOperator`s must have shape `[B1, ..., Bb, d, d]`,
`b >= 0`, i.e., characterizes `b`-batches of `d x d` matrices
quadrature_size: Python `int` scalar representing number of
quadrature points. Larger `quadrature_size` means `q_N(x)` better
approximates `p(x)`.
quadrature_fn: Python callable taking `normal_loc`, `normal_scale`,
`quadrature_size`, `validate_args` and returning `tuple(grid, probs)`
representing the SoftmaxNormal grid and corresponding normalized weight.
normalized) weight.
Default value: `quadrature_scheme_softmaxnormal_quantiles`.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
ValueError: if `not scale or len(scale) < 2`.
ValueError: if `len(loc) != len(scale)`
ValueError: if `quadrature_grid_and_probs is not None` and
`len(quadrature_grid_and_probs[0]) != len(quadrature_grid_and_probs[1])`
ValueError: if `validate_args` and any not scale.is_positive_definite.
TypeError: if any scale.dtype != scale[0].dtype.
TypeError: if any loc.dtype != scale[0].dtype.
NotImplementedError: if `len(scale) != 2`.
ValueError: if `not distribution.is_scalar_batch`.
ValueError: if `not distribution.is_scalar_event`.
"""
parameters = distribution_util.parent_frame_arguments()
with ops.name_scope(name, values=[mix_loc, temperature]) as name:
if not scale or len(scale) < 2:
raise ValueError("Must specify list (or list-like object) of scale "
"LinearOperators, one for each component with "
"num_component >= 2.")
if loc is None:
loc = [None]*len(scale)
if len(loc) != len(scale):
raise ValueError("loc/scale must be same-length lists "
"(or same-length list-like objects).")
dtype = scale[0].dtype.base_dtype
loc = [ops.convert_to_tensor(loc_, dtype=dtype, name="loc{}".format(k))
if loc_ is not None else None
for k, loc_ in enumerate(loc)]
for k, scale_ in enumerate(scale):
if validate_args and not scale_.is_positive_definite:
raise ValueError("scale[{}].is_positive_definite = {} != True".format(
k, scale_.is_positive_definite))
if scale_.dtype.base_dtype != dtype:
raise TypeError(
"dtype mismatch; scale[{}].base_dtype=\"{}\" != \"{}\"".format(
k, scale_.dtype.base_dtype.name, dtype.name))
self._endpoint_affine = [
AffineLinearOperator(shift=loc_,
scale=scale_,
validate_args=validate_args,
name="endpoint_affine_{}".format(k))
for k, (loc_, scale_) in enumerate(zip(loc, scale))]
# TODO(jvdillon): Remove once we support k-mixtures.
# We make this assertion here because otherwise `grid` would need to be a
# vector not a scalar.
if len(scale) != 2:
raise NotImplementedError("Currently only bimixtures are supported; "
"len(scale)={} is not 2.".format(len(scale)))
mix_loc = ops.convert_to_tensor(
mix_loc, dtype=dtype, name="mix_loc")
temperature = ops.convert_to_tensor(
temperature, dtype=dtype, name="temperature")
self._grid, probs = tuple(quadrature_fn(
mix_loc / temperature,
1. / temperature,
quadrature_size,
validate_args))
# Note: by creating the logits as `log(prob)` we ensure that
# `self.mixture_distribution.logits` is equivalent to
# `math_ops.log(self.mixture_distribution.probs)`.
self._mixture_distribution = categorical_lib.Categorical(
logits=math_ops.log(probs),
validate_args=validate_args,
allow_nan_stats=allow_nan_stats)
asserts = distribution_util.maybe_check_scalar_distribution(
distribution, dtype, validate_args)
if asserts:
self._grid = control_flow_ops.with_dependencies(
asserts, self._grid)
self._distribution = distribution
self._interpolated_affine = [
AffineLinearOperator(shift=loc_,
scale=scale_,
validate_args=validate_args,
name="interpolated_affine_{}".format(k))
for k, (loc_, scale_) in enumerate(zip(
interpolate_loc(self._grid, loc),
interpolate_scale(self._grid, scale)))]
[
self._batch_shape_,
self._batch_shape_tensor_,
self._event_shape_,
self._event_shape_tensor_,
] = determine_batch_event_shapes(self._grid,
self._endpoint_affine)
super(VectorDiffeomixture, self).__init__(
dtype=dtype,
# We hard-code `FULLY_REPARAMETERIZED` because when
# `validate_args=True` we verify that indeed
# `distribution.reparameterization_type == FULLY_REPARAMETERIZED`. A
# distribution which is a function of only non-trainable parameters
# also implies we can use `FULLY_REPARAMETERIZED`. However, we cannot
# easily test for that possibility thus we use `validate_args=False`
# as a "back-door" to allow users a way to use non
# `FULLY_REPARAMETERIZED` distribution. In such cases IT IS THE USERS
# RESPONSIBILITY to verify that the base distribution is a function of
# non-trainable parameters.
reparameterization_type=distribution_lib.FULLY_REPARAMETERIZED,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
parameters=parameters,
graph_parents=(
distribution._graph_parents # pylint: disable=protected-access
+ [loc_ for loc_ in loc if loc_ is not None]
+ [p for scale_ in scale for p in scale_.graph_parents]),
name=name)
def __init__(self,
df,
scale_operator,
cholesky_input_output_matrices=False,
validate_args=False,
allow_nan_stats=True,
name=None):
"""Construct Wishart distributions.
Args:
df: `float` or `double` tensor, the degrees of freedom of the
distribution(s). `df` must be greater than or equal to `k`.
scale_operator: `float` or `double` instance of `LinearOperator`.
cholesky_input_output_matrices: Python `bool`. Any function which whose
input or output is a matrix assumes the input is Cholesky and returns a
Cholesky factored matrix. Example `log_prob` input takes a Cholesky and
`sample_n` returns a Cholesky when
`cholesky_input_output_matrices=True`.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
TypeError: if scale is not floating-type
TypeError: if scale.dtype != df.dtype
ValueError: if df < k, where scale operator event shape is
`(k, k)`
"""
parameters = distribution_util.parent_frame_arguments()
self._cholesky_input_output_matrices = cholesky_input_output_matrices
with ops.name_scope(name) as name:
with ops.name_scope("init", values=[df, scale_operator]):
if not scale_operator.dtype.is_floating:
raise TypeError(
"scale_operator.dtype=%s is not a floating-point type" %
scale_operator.dtype)
if not scale_operator.is_square:
print(scale_operator.to_dense().eval())
raise ValueError("scale_operator must be square.")
self._scale_operator = scale_operator
self._df = ops.convert_to_tensor(
df,
dtype=scale_operator.dtype,
name="df")
contrib_tensor_util.assert_same_float_dtype(
(self._df, self._scale_operator))
if (self._scale_operator.shape.ndims is None or
self._scale_operator.shape[-1].value is None):
self._dimension = math_ops.cast(
self._scale_operator.domain_dimension_tensor(),
dtype=self._scale_operator.dtype, name="dimension")
else:
self._dimension = ops.convert_to_tensor(
self._scale_operator.shape[-1].value,
dtype=self._scale_operator.dtype, name="dimension")
df_val = tensor_util.constant_value(self._df)
dim_val = tensor_util.constant_value(self._dimension)
if df_val is not None and dim_val is not None:
df_val = np.asarray(df_val)
if not df_val.shape:
df_val = [df_val]
if any(df_val < dim_val):
raise ValueError(
"Degrees of freedom (df = %s) cannot be less than "
"dimension of scale matrix (scale.dimension = %s)"
% (df_val, dim_val))
elif validate_args:
assertions = check_ops.assert_less_equal(
self._dimension, self._df,
message=("Degrees of freedom (df = %s) cannot be "
"less than dimension of scale matrix "
"(scale.dimension = %s)" %
(self._dimension, self._df)))
self._df = control_flow_ops.with_dependencies(
[assertions], self._df)
super(_WishartLinearOperator, self).__init__(
dtype=self._scale_operator.dtype,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
reparameterization_type=distribution.FULLY_REPARAMETERIZED,
parameters=parameters,
graph_parents=([self._df, self._dimension] +
self._scale_operator.graph_parents),
name=name)
def __init__(self,
loc=None,
scale_diag=None,
scale_identity_multiplier=None,
scale_perturb_factor=None,
scale_perturb_diag=None,
validate_args=False,
allow_nan_stats=True,
name="MultivariateNormalDiagPlusLowRank"):
"""Construct Multivariate Normal distribution on `R^k`.
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this.
Recall that `covariance = scale @ scale.T`. A (non-batch) `scale` matrix is:
```none
scale = diag(scale_diag + scale_identity_multiplier ones(k)) +
scale_perturb_factor @ diag(scale_perturb_diag) @ scale_perturb_factor.T
```
where:
* `scale_diag.shape = [k]`,
* `scale_identity_multiplier.shape = []`,
* `scale_perturb_factor.shape = [k, r]`, typically `k >> r`, and,
* `scale_perturb_diag.shape = [r]`.
Additional leading dimensions (if any) will index batches.
If both `scale_diag` and `scale_identity_multiplier` are `None`, then
`scale` is the Identity matrix.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale_diag: Non-zero, floating-point `Tensor` representing a diagonal
matrix added to `scale`. May have shape `[B1, ..., Bb, k]`, `b >= 0`,
and characterizes `b`-batches of `k x k` diagonal matrices added to
`scale`. When both `scale_identity_multiplier` and `scale_diag` are
`None` then `scale` is the `Identity`.
scale_identity_multiplier: Non-zero, floating-point `Tensor` representing
a scaled-identity-matrix added to `scale`. May have shape
`[B1, ..., Bb]`, `b >= 0`, and characterizes `b`-batches of scaled
`k x k` identity matrices added to `scale`. When both
`scale_identity_multiplier` and `scale_diag` are `None` then `scale` is
the `Identity`.
scale_perturb_factor: Floating-point `Tensor` representing a rank-`r`
perturbation added to `scale`. May have shape `[B1, ..., Bb, k, r]`,
`b >= 0`, and characterizes `b`-batches of rank-`r` updates to `scale`.
When `None`, no rank-`r` update is added to `scale`.
scale_perturb_diag: Floating-point `Tensor` representing a diagonal matrix
inside the rank-`r` perturbation added to `scale`. May have shape
`[B1, ..., Bb, r]`, `b >= 0`, and characterizes `b`-batches of `r x r`
diagonal matrices inside the perturbation added to `scale`. When
`None`, an identity matrix is used inside the perturbation. Can only be
specified if `scale_perturb_factor` is also specified.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
ValueError: if at most `scale_identity_multiplier` is specified.
"""
parameters = distribution_util.parent_frame_arguments()
def _convert_to_tensor(x, name):
return None if x is None else ops.convert_to_tensor(x, name=name)
with ops.name_scope(name) as name:
with ops.name_scope("init", values=[
loc, scale_diag, scale_identity_multiplier, scale_perturb_factor,
scale_perturb_diag]):
has_low_rank = (scale_perturb_factor is not None or
scale_perturb_diag is not None)
scale = distribution_util.make_diag_scale(
loc=loc,
scale_diag=scale_diag,
scale_identity_multiplier=scale_identity_multiplier,
validate_args=validate_args,
assert_positive=has_low_rank)
scale_perturb_factor = _convert_to_tensor(
scale_perturb_factor,
name="scale_perturb_factor")
scale_perturb_diag = _convert_to_tensor(
scale_perturb_diag,
name="scale_perturb_diag")
if has_low_rank:
scale = linalg.LinearOperatorLowRankUpdate(
scale,
u=scale_perturb_factor,
diag_update=scale_perturb_diag,
is_diag_update_positive=scale_perturb_diag is None,
is_non_singular=True, # Implied by is_positive_definite=True.
is_self_adjoint=True,
is_positive_definite=True,
is_square=True)
super(MultivariateNormalDiagPlusLowRank, self).__init__(
loc=loc,
scale=scale,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters
def __init__(self,
df,
scale_operator,
cholesky_input_output_matrices=False,
validate_args=False,
allow_nan_stats=True,
name=None):
"""Construct Wishart distributions.
Args:
df: `float` or `double` tensor, the degrees of freedom of the
distribution(s). `df` must be greater than or equal to `k`.
scale_operator: `float` or `double` instance of `LinearOperator`.
cholesky_input_output_matrices: Python `bool`. Any function which whose
input or output is a matrix assumes the input is Cholesky and returns a
Cholesky factored matrix. Example `log_prob` input takes a Cholesky and
`sample_n` returns a Cholesky when
`cholesky_input_output_matrices=True`.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
TypeError: if scale is not floating-type
TypeError: if scale.dtype != df.dtype
ValueError: if df < k, where scale operator event shape is
`(k, k)`
"""
parameters = distribution_util.parent_frame_arguments()
self._cholesky_input_output_matrices = cholesky_input_output_matrices
with ops.name_scope(name) as name:
with ops.name_scope("init", values=[df, scale_operator]):
if not scale_operator.dtype.is_floating:
raise TypeError(
"scale_operator.dtype=%s is not a floating-point type"
% scale_operator.dtype)
if not scale_operator.is_square:
print(scale_operator.to_dense().eval())
raise ValueError("scale_operator must be square.")
self._scale_operator = scale_operator
self._df = ops.convert_to_tensor(df,
dtype=scale_operator.dtype,
name="df")
contrib_tensor_util.assert_same_float_dtype(
(self._df, self._scale_operator))
if (self._scale_operator.shape.ndims is None
or self._scale_operator.shape[-1].value is None):
self._dimension = math_ops.cast(
self._scale_operator.domain_dimension_tensor(),
dtype=self._scale_operator.dtype,
name="dimension")
else:
self._dimension = ops.convert_to_tensor(
self._scale_operator.shape[-1].value,
dtype=self._scale_operator.dtype,
name="dimension")
df_val = tensor_util.constant_value(self._df)
dim_val = tensor_util.constant_value(self._dimension)
if df_val is not None and dim_val is not None:
df_val = np.asarray(df_val)
if not df_val.shape:
df_val = [df_val]
if any(df_val < dim_val):
raise ValueError(
"Degrees of freedom (df = %s) cannot be less than "
"dimension of scale matrix (scale.dimension = %s)"
% (df_val, dim_val))
elif validate_args:
assertions = check_ops.assert_less_equal(
self._dimension,
self._df,
message=("Degrees of freedom (df = %s) cannot be "
"less than dimension of scale matrix "
"(scale.dimension = %s)" %
(self._dimension, self._df)))
self._df = control_flow_ops.with_dependencies([assertions],
self._df)
super(_WishartLinearOperator, self).__init__(
dtype=self._scale_operator.dtype,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
reparameterization_type=distribution.FULLY_REPARAMETERIZED,
parameters=parameters,
graph_parents=([self._df, self._dimension] +
self._scale_operator.graph_parents),
name=name)
def __init__(self,
loc=None,
scale_diag=None,
scale_identity_multiplier=None,
scale_perturb_factor=None,
scale_perturb_diag=None,
validate_args=False,
allow_nan_stats=True,
name="MultivariateNormalDiagPlusLowRank"):
"""Construct Multivariate Normal distribution on `R^k`.
The `batch_shape` is the broadcast shape between `loc` and `scale`
arguments.
The `event_shape` is given by last dimension of the matrix implied by
`scale`. The last dimension of `loc` (if provided) must broadcast with this.
Recall that `covariance = scale @ scale.T`. A (non-batch) `scale` matrix is:
```none
scale = diag(scale_diag + scale_identity_multiplier ones(k)) +
scale_perturb_factor @ diag(scale_perturb_diag) @ scale_perturb_factor.T
```
where:
* `scale_diag.shape = [k]`,
* `scale_identity_multiplier.shape = []`,
* `scale_perturb_factor.shape = [k, r]`, typically `k >> r`, and,
* `scale_perturb_diag.shape = [r]`.
Additional leading dimensions (if any) will index batches.
If both `scale_diag` and `scale_identity_multiplier` are `None`, then
`scale` is the Identity matrix.
Args:
loc: Floating-point `Tensor`. If this is set to `None`, `loc` is
implicitly `0`. When specified, may have shape `[B1, ..., Bb, k]` where
`b >= 0` and `k` is the event size.
scale_diag: Non-zero, floating-point `Tensor` representing a diagonal
matrix added to `scale`. May have shape `[B1, ..., Bb, k]`, `b >= 0`,
and characterizes `b`-batches of `k x k` diagonal matrices added to
`scale`. When both `scale_identity_multiplier` and `scale_diag` are
`None` then `scale` is the `Identity`.
scale_identity_multiplier: Non-zero, floating-point `Tensor` representing
a scaled-identity-matrix added to `scale`. May have shape
`[B1, ..., Bb]`, `b >= 0`, and characterizes `b`-batches of scaled
`k x k` identity matrices added to `scale`. When both
`scale_identity_multiplier` and `scale_diag` are `None` then `scale` is
the `Identity`.
scale_perturb_factor: Floating-point `Tensor` representing a rank-`r`
perturbation added to `scale`. May have shape `[B1, ..., Bb, k, r]`,
`b >= 0`, and characterizes `b`-batches of rank-`r` updates to `scale`.
When `None`, no rank-`r` update is added to `scale`.
scale_perturb_diag: Floating-point `Tensor` representing a diagonal matrix
inside the rank-`r` perturbation added to `scale`. May have shape
`[B1, ..., Bb, r]`, `b >= 0`, and characterizes `b`-batches of `r x r`
diagonal matrices inside the perturbation added to `scale`. When
`None`, an identity matrix is used inside the perturbation. Can only be
specified if `scale_perturb_factor` is also specified.
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.
name: Python `str` name prefixed to Ops created by this class.
Raises:
ValueError: if at most `scale_identity_multiplier` is specified.
"""
parameters = distribution_util.parent_frame_arguments()
def _convert_to_tensor(x, name):
return None if x is None else ops.convert_to_tensor(x, name=name)
with ops.name_scope(name) as name:
with ops.name_scope("init",
values=[
loc, scale_diag, scale_identity_multiplier,
scale_perturb_factor, scale_perturb_diag
]):
has_low_rank = (scale_perturb_factor is not None
or scale_perturb_diag is not None)
scale = distribution_util.make_diag_scale(
loc=loc,
scale_diag=scale_diag,
scale_identity_multiplier=scale_identity_multiplier,
validate_args=validate_args,
assert_positive=has_low_rank)
scale_perturb_factor = _convert_to_tensor(
scale_perturb_factor, name="scale_perturb_factor")
scale_perturb_diag = _convert_to_tensor(
scale_perturb_diag, name="scale_perturb_diag")
if has_low_rank:
scale = linalg.LinearOperatorLowRankUpdate(
scale,
u=scale_perturb_factor,
diag_update=scale_perturb_diag,
is_diag_update_positive=scale_perturb_diag is None,
is_non_singular=
True, # Implied by is_positive_definite=True.
is_self_adjoint=True,
is_positive_definite=True,
is_square=True)
super(MultivariateNormalDiagPlusLowRank,
self).__init__(loc=loc,
scale=scale,
validate_args=validate_args,
allow_nan_stats=allow_nan_stats,
name=name)
self._parameters = parameters