Class SumVectorGaussianOp

Provides outgoing messages for Sum(IList<Vector>), given random arguments to the function.

Inheritance

Object

SumVectorGaussianOp

Inherited Members

Object.Equals(Object)

Object.Equals(Object, Object)

Object.GetHashCode()

Object.GetType()

Object.MemberwiseClone()

Object.ReferenceEquals(Object, Object)

Object.ToString()

Namespace: Microsoft.ML.Probabilistic.Factors

Assembly: Microsoft.ML.Probabilistic.dll

Syntax

[FactorMethod(typeof(Factor), "Sum", new Type[]{typeof(Vector[])})]
[Quality(QualityBand.Stable)]
public static class SumVectorGaussianOp

Methods

ArrayAverageConditional(VectorGaussian, VectorGaussian, VectorGaussian[], VectorGaussian[])

EP message to array.

Declaration

public static VectorGaussian[] ArrayAverageConditional(VectorGaussian sum, VectorGaussian to_sum, VectorGaussian[] array, VectorGaussian[] result)

Parameters

Type	Name	Description
VectorGaussian	sum	Incoming message from sum. Must be a proper distribution. If any element is uniform, the result will be uniform.
VectorGaussian	to_sum	Outgoing message to sum.
VectorGaussian[]	array	Incoming message from array.
VectorGaussian[]	result	Modified to contain the outgoing message.

Returns

Type	Description
VectorGaussian[]	result

Remarks

The outgoing message is a distribution matching the moments of array as the random arguments are varied. The formula is proj[p(array) sum_(sum) p(sum) factor(sum,array)]/p(array).

Exceptions

Type	Condition
ImproperMessageException	sum is not a proper distribution.

ArrayAverageConditional<TVectorGaussianList>(VectorGaussian, VectorGaussian, IList<VectorGaussian>, TVectorGaussianList)

EP message to array.

Declaration

public static TVectorGaussianList ArrayAverageConditional<TVectorGaussianList>(VectorGaussian sum, VectorGaussian to_sum, IList<VectorGaussian> array, TVectorGaussianList result)
    where TVectorGaussianList : IList<VectorGaussian>, SettableToUniform

Parameters

Type	Name	Description
VectorGaussian	sum	Incoming message from sum. Must be a proper distribution. If any element is uniform, the result will be uniform.
VectorGaussian	to_sum	Outgoing message to sum.
IList<VectorGaussian>	array	Incoming message from array.
TVectorGaussianList	result	Modified to contain the outgoing message.

Returns

Type	Description
TVectorGaussianList	result

Type Parameters

Name	Description
TVectorGaussianList

Remarks

The outgoing message is a distribution matching the moments of array as the random arguments are varied. The formula is proj[p(array) sum_(sum) p(sum) factor(sum,array)]/p(array).

Exceptions

Type	Condition
ImproperMessageException	sum is not a proper distribution.

ArrayAverageConditional<TVectorGaussianList>(Vector, IList<VectorGaussian>, TVectorGaussianList)

EP message to array.

Declaration

public static TVectorGaussianList ArrayAverageConditional<TVectorGaussianList>(Vector sum, IList<VectorGaussian> array, TVectorGaussianList result)
    where TVectorGaussianList : IList<VectorGaussian>, SettableToUniform

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<VectorGaussian>	array	Incoming message from array.
TVectorGaussianList	result	Modified to contain the outgoing message.

Returns

Type	Description
TVectorGaussianList	result

Type Parameters

Name	Description
TVectorGaussianList	A list of VectorGaussian distributions which may be set to uniform.

Remarks

The outgoing message is the factor viewed as a function of array conditioned on the given values.

ArrayAverageLogarithm<TVectorGaussianList>(VectorGaussian, IList<VectorGaussian>, TVectorGaussianList)

VMP message to array.

Declaration

public static TVectorGaussianList ArrayAverageLogarithm<TVectorGaussianList>(VectorGaussian sum, IList<VectorGaussian> array, TVectorGaussianList to_array)
    where TVectorGaussianList : IList<VectorGaussian>

Parameters

Type	Name	Description
VectorGaussian	sum	Incoming message from sum. Must be a proper distribution. If any element is uniform, the result will be uniform.
IList<VectorGaussian>	array	Incoming message from array. Must be a proper distribution. If any element is uniform, the result will be uniform.
TVectorGaussianList	to_array	Previous outgoing message to array.

Returns

Type	Description
TVectorGaussianList	The outgoing VMP message to the array argument.

Type Parameters

Name	Description
TVectorGaussianList	A list of VectorGaussian distributions.

Remarks

The outgoing message is the factor viewed as a function of array with sum integrated out. The formula is sum_sum p(sum) factor(sum,array).

Exceptions

Type	Condition
ImproperMessageException	sum is not a proper distribution.
ImproperMessageException	array is not a proper distribution.

ArrayAverageLogarithm<TVectorGaussianList>(Vector, IList<VectorGaussian>, TVectorGaussianList)

VMP message to array.

Declaration

public static TVectorGaussianList ArrayAverageLogarithm<TVectorGaussianList>(Vector sum, IList<VectorGaussian> array, TVectorGaussianList result)
    where TVectorGaussianList : IList<VectorGaussian>

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<VectorGaussian>	array	Incoming message from array. Must be a proper distribution. If any element is uniform, the result will be uniform.
TVectorGaussianList	result	Modified to contain the outgoing message.

Returns

Type	Description
TVectorGaussianList	result

Type Parameters

Name	Description
TVectorGaussianList	A list of VectorGaussian distributions.

Remarks

The outgoing message is the factor viewed as a function of array conditioned on the given values.

Exceptions

Type	Condition
ImproperMessageException	array is not a proper distribution.

ArrayAverageLogarithm1<TVectorGaussianList>(VectorGaussian, IList<VectorGaussian>, TVectorGaussianList)

Declaration

public static TVectorGaussianList ArrayAverageLogarithm1<TVectorGaussianList>(VectorGaussian sum, IList<VectorGaussian> array, TVectorGaussianList to_array)
    where TVectorGaussianList : IList<VectorGaussian>

Parameters

Type	Name	Description
VectorGaussian	sum	Incoming message from sum. Must be a proper distribution. If any element is uniform, the result will be uniform.
IList<VectorGaussian>	array	Incoming message from array. Must be a proper distribution. If any element is uniform, the result will be uniform.
TVectorGaussianList	to_array	Previous outgoing message to array.

Returns

Type	Description
TVectorGaussianList

Type Parameters

Name	Description
TVectorGaussianList	A list of VectorGaussian distributions.

Remarks

Exceptions

Type	Condition
ImproperMessageException	sum is not a proper distribution.
ImproperMessageException	array is not a proper distribution.

AverageLogFactor()

Evidence message for VMP.

Declaration

public static double AverageLogFactor()

Returns

Type	Description
Double	Zero.

Remarks

The formula for the result is log(factor(sum,array)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

AverageLogFactor(Vector, IList<Vector>)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Vector sum, IList<Vector> array)

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<Vector>	array	Constant value for array.

Returns

Type	Description
Double	Zero.

Remarks

The formula for the result is log(factor(sum,array)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

LogAverageFactor(VectorGaussian, VectorGaussian)

Evidence message for EP.

Declaration

public static double LogAverageFactor(VectorGaussian sum, VectorGaussian to_sum)

Parameters

Type	Name	Description
VectorGaussian	sum	Incoming message from sum. Must be a proper distribution. If any element is uniform, the result will be uniform.
VectorGaussian	to_sum	Outgoing message to sum.

Returns

Type	Description
Double	Logarithm of the factor's average value across the given argument distributions.

Remarks

The formula for the result is log(sum_(sum) p(sum) factor(sum,array)).

Exceptions

Type	Condition
ImproperMessageException	sum is not a proper distribution.

LogAverageFactor(Vector, IList<VectorGaussian>)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Vector sum, IList<VectorGaussian> array)

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<VectorGaussian>	array	Incoming message from array.

Returns

Type	Description
Double	Logarithm of the factor's average value across the given argument distributions.

Remarks

The formula for the result is log(sum_(array) p(array) factor(sum,array)).

LogAverageFactor(Vector, IList<Vector>)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Vector sum, IList<Vector> array)

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<Vector>	array	Constant value for array.

Returns

Type	Description
Double	Logarithm of the factor's average value across the given argument distributions.

Remarks

The formula for the result is log(factor(sum,array)).

LogEvidenceRatio(VectorGaussian)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(VectorGaussian sum)

Parameters

Type	Name	Description
VectorGaussian	sum	Incoming message from sum.

Returns

Type	Description
Double	Logarithm of the factor's contribution the EP model evidence.

Remarks

The formula for the result is log(sum_(sum) p(sum) factor(sum,array) / sum_sum p(sum) messageTo(sum)). Adding up these values across all factors and variables gives the log-evidence estimate for EP.

LogEvidenceRatio(Vector, IList<VectorGaussian>)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Vector sum, IList<VectorGaussian> array)

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<VectorGaussian>	array	Incoming message from array.

Returns

Type	Description
Double	Logarithm of the factor's contribution the EP model evidence.

Remarks

The formula for the result is log(sum_(array) p(array) factor(sum,array)). Adding up these values across all factors and variables gives the log-evidence estimate for EP.

LogEvidenceRatio(Vector, IList<Vector>)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Vector sum, IList<Vector> array)

Parameters

Type	Name	Description
Vector	sum	Constant value for sum.
IList<Vector>	array	Constant value for array.

Returns

Type	Description
Double	Logarithm of the factor's contribution the EP model evidence.

Remarks

The formula for the result is log(factor(sum,array)). Adding up these values across all factors and variables gives the log-evidence estimate for EP.

SumAverageConditional(IList<VectorGaussian>, VectorGaussian)

EP message to sum.

Declaration

public static VectorGaussian SumAverageConditional(IList<VectorGaussian> array, VectorGaussian result)

Parameters

Type	Name	Description
IList<VectorGaussian>	array	Incoming message from array.
VectorGaussian	result	Modified to contain the outgoing message.

Returns

Type	Description
VectorGaussian	result

Remarks

The outgoing message is a distribution matching the moments of sum as the random arguments are varied. The formula is proj[p(sum) sum_(array) p(array) factor(sum,array)]/p(sum).

SumAverageLogarithm(IList<VectorGaussian>, VectorGaussian)

VMP message to sum.

Declaration

public static VectorGaussian SumAverageLogarithm(IList<VectorGaussian> array, VectorGaussian result)

Parameters

Type	Name	Description
IList<VectorGaussian>	array	Incoming message from array.
VectorGaussian	result	Modified to contain the outgoing message.

Returns

Type	Description
VectorGaussian	result

Remarks

The outgoing message is a distribution matching the moments of sum as the random arguments are varied. The formula is proj[sum_(array) p(array) factor(sum,array)].