Class InnerProductPartialCovarianceOp

Inheritance

Object

InnerProductPartialCovarianceOp

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), "InnerProduct", new Type[]{typeof(double[]), typeof(Vector)})]
[Buffers(new string[]{"MeanOfB", "CovarianceOfB"})]
[Quality(QualityBand.Preview)]
public static class InnerProductPartialCovarianceOp

Methods

AAverageLogarithm(Gaussian, DistributionStructArray<Gaussian, Double>, VectorGaussian, Vector, PositiveDefiniteMatrix, DistributionStructArray<Gaussian, Double>)

VMP message to A.

Declaration

public static DistributionStructArray<Gaussian, double> AAverageLogarithm(Gaussian X, DistributionStructArray<Gaussian, double> A, VectorGaussian B, Vector MeanOfB, PositiveDefiniteMatrix CovarianceOfB, DistributionStructArray<Gaussian, double> result)

Parameters

Type	Name	Description
Gaussian	X	Incoming message from X. Must be a proper distribution. If uniform, the result will be uniform.
DistributionStructArray<Gaussian, Double>	A	Incoming message from A.
VectorGaussian	B	Incoming message from B. Must be a proper distribution. If any element is uniform, the result will be uniform.
Vector	MeanOfB	Buffer MeanOfB.
PositiveDefiniteMatrix	CovarianceOfB	Buffer CovarianceOfB.
DistributionStructArray<Gaussian, Double>	result	Modified to contain the outgoing message.

Returns

Type	Description
DistributionStructArray<Gaussian, Double>	result

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except A. Because the factor is deterministic, X is integrated out before taking the logarithm. The formula is exp(sum_(B) p(B) log(sum_X p(X) factor(X,A,B))).

Exceptions

Type	Condition
ImproperMessageException	X is not a proper distribution.
ImproperMessageException	B 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(X,A,B)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

BAverageLogarithm(Gaussian, DistributionStructArray<Gaussian, Double>, VectorGaussian)

VMP message to B.

Declaration

public static VectorGaussian BAverageLogarithm(Gaussian X, [SkipIfAllUniform] DistributionStructArray<Gaussian, double> A, VectorGaussian result)

Parameters

Type	Name	Description
Gaussian	X	Incoming message from X. Must be a proper distribution. If uniform, the result will be uniform.
DistributionStructArray<Gaussian, Double>	A	Incoming message from A. Must be a proper distribution. If all elements are uniform, the result will be uniform.
VectorGaussian	result	Modified to contain the outgoing message.

Returns

Type	Description
VectorGaussian	result

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except B. Because the factor is deterministic, X is integrated out before taking the logarithm. The formula is exp(sum_(A) p(A) log(sum_X p(X) factor(X,A,B))).

Exceptions

Type	Condition
ImproperMessageException	X is not a proper distribution.
ImproperMessageException	A is not a proper distribution.

BAverageLogarithm(Gaussian, Double[], VectorGaussian)

VMP message to B.

Declaration

public static VectorGaussian BAverageLogarithm(Gaussian X, [SkipIfAllUniform] double[] A, VectorGaussian result)

Parameters

Type	Name	Description
Gaussian	X	Incoming message from X. Must be a proper distribution. If uniform, the result will be uniform.
Double[]	A	Constant value for A.
VectorGaussian	result	Modified to contain the outgoing message.

Returns

Type	Description
VectorGaussian	result

Remarks

The outgoing message is the factor viewed as a function of B with X integrated out. The formula is sum_X p(X) factor(X,A,B).

Exceptions

Type	Condition
ImproperMessageException	X is not a proper distribution.

CovarianceOfB(VectorGaussian, PositiveDefiniteMatrix)

Update the buffer CovarianceOfB.

Declaration

public static PositiveDefiniteMatrix CovarianceOfB(VectorGaussian B, PositiveDefiniteMatrix result)

Parameters

Type	Name	Description
VectorGaussian	B	Incoming message from B. Must be a proper distribution. If any element is uniform, the result will be uniform.
PositiveDefiniteMatrix	result	Modified to contain the outgoing message.

Returns

Type	Description
PositiveDefiniteMatrix	result

Remarks

Exceptions

Type	Condition
ImproperMessageException	B is not a proper distribution.

CovarianceOfBInit(VectorGaussian)

Initialize the buffer CovarianceOfB.

Declaration

public static PositiveDefiniteMatrix CovarianceOfBInit(VectorGaussian B)

Parameters

Type	Name	Description
VectorGaussian	B	Incoming message from B.

Returns

Type	Description
PositiveDefiniteMatrix	Initial value of buffer CovarianceOfB.

Remarks

Eaat(DistributionStructArray<Gaussian, Double>, PositiveDefiniteMatrix)

Declaration

public static PositiveDefiniteMatrix Eaat(DistributionStructArray<Gaussian, double> A, PositiveDefiniteMatrix result)

Parameters

Type	Name	Description
DistributionStructArray<Gaussian, Double>	A	Incoming message from A.
PositiveDefiniteMatrix	result	Modified to contain the outgoing message.

Returns

Type	Description
PositiveDefiniteMatrix	result

Remarks

EaatInit(DistributionStructArray<Gaussian, Double>)

Declaration

public static PositiveDefiniteMatrix EaatInit(DistributionStructArray<Gaussian, double> A)

Parameters

Type	Name	Description
DistributionStructArray<Gaussian, Double>	A	Incoming message from A.

Returns

Type	Description
PositiveDefiniteMatrix

Remarks

Ebbt(PositiveDefiniteMatrix, Vector, PositiveDefiniteMatrix)

Declaration

public static PositiveDefiniteMatrix Ebbt(PositiveDefiniteMatrix CovarianceOfB, Vector MeanOfB, PositiveDefiniteMatrix result)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	CovarianceOfB	Buffer CovarianceOfB.
Vector	MeanOfB	Buffer MeanOfB.
PositiveDefiniteMatrix	result	Modified to contain the outgoing message.

Returns

Type	Description
PositiveDefiniteMatrix	result

Remarks

EbbtInit(VectorGaussian)

Declaration

public static PositiveDefiniteMatrix EbbtInit(VectorGaussian B)

Parameters

Type	Name	Description
VectorGaussian	B	Incoming message from B.

Returns

Type	Description
PositiveDefiniteMatrix

Remarks

MeanOfB(VectorGaussian, PositiveDefiniteMatrix, Vector)

Update the buffer MeanOfB.

Declaration

public static Vector MeanOfB(VectorGaussian B, PositiveDefiniteMatrix CovarianceOfB, Vector result)

Parameters

Type	Name	Description
VectorGaussian	B	Incoming message from B. Must be a proper distribution. If any element is uniform, the result will be uniform.
PositiveDefiniteMatrix	CovarianceOfB	Buffer CovarianceOfB.
Vector	result	Modified to contain the outgoing message.

Returns

Type	Description
Vector	result

Remarks

Exceptions

Type	Condition
ImproperMessageException	B is not a proper distribution.

MeanOfBInit(VectorGaussian)

Initialize the buffer MeanOfB.

Declaration

public static Vector MeanOfBInit(VectorGaussian B)

Parameters

Type	Name	Description
VectorGaussian	B	Incoming message from B.

Returns

Type	Description
Vector	Initial value of buffer MeanOfB.

Remarks

XAverageLogarithm(DistributionStructArray<Gaussian, Double>, VectorGaussian, Vector, PositiveDefiniteMatrix)

VMP message to X.

Declaration

public static Gaussian XAverageLogarithm([SkipIfAllUniform] DistributionStructArray<Gaussian, double> A, [SkipIfAllUniform] VectorGaussian B, Vector MeanOfB, PositiveDefiniteMatrix CovarianceOfB)

Parameters

Type	Name	Description
DistributionStructArray<Gaussian, Double>	A	Incoming message from A. Must be a proper distribution. If all elements are uniform, the result will be uniform.
VectorGaussian	B	Incoming message from B. Must be a proper distribution. If all elements are uniform, the result will be uniform.
Vector	MeanOfB	Buffer MeanOfB.
PositiveDefiniteMatrix	CovarianceOfB	Buffer CovarianceOfB.

Returns

Type	Description
Gaussian	The outgoing VMP message to the X argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	A is not a proper distribution.
ImproperMessageException	B is not a proper distribution.

XAverageLogarithm(Double[], VectorGaussian, Vector, PositiveDefiniteMatrix)

VMP message to X.

Declaration

public static Gaussian XAverageLogarithm([SkipIfAllUniform] double[] A, [SkipIfAllUniform] VectorGaussian B, Vector MeanOfB, PositiveDefiniteMatrix CovarianceOfB)

Parameters

Type	Name	Description
Double[]	A	Constant value for A.
VectorGaussian	B	Incoming message from B. Must be a proper distribution. If all elements are uniform, the result will be uniform.
Vector	MeanOfB	Buffer MeanOfB.
PositiveDefiniteMatrix	CovarianceOfB	Buffer CovarianceOfB.

Returns

Type	Description
Gaussian	The outgoing VMP message to the X argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	B is not a proper distribution.

XAverageLogarithmInit()

Declaration

public static Gaussian XAverageLogarithmInit()

Returns

Type	Description
Gaussian

Remarks