Class DoubleMinusVmpOp

Provides outgoing messages for Difference(Double, Double), given random arguments to the function.

Inheritance

Object

DoubleMinusVmpOp

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), "Difference", new Type[]{typeof(double), typeof(double)})]
[Quality(QualityBand.Stable)]
public static class DoubleMinusVmpOp

Methods

AAverageLogarithm(Gaussian, Gaussian)

VMP message to a.

Declaration

public static Gaussian AAverageLogarithm(Gaussian Difference, Gaussian b)

Parameters

Type	Name	Description
Gaussian	Difference	Incoming message from difference. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	b	Incoming message from b. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

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, difference is integrated out before taking the logarithm. The formula is exp(sum_(b) p(b) log(sum_difference p(difference) factor(difference,a,b))).

Exceptions

Type	Condition
ImproperMessageException	Difference is not a proper distribution.
ImproperMessageException	b is not a proper distribution.

AAverageLogarithm(Gaussian, Double)

VMP message to a.

Declaration

public static Gaussian AAverageLogarithm(Gaussian Difference, double b)

Parameters

Type	Name	Description
Gaussian	Difference	Incoming message from difference. Must be a proper distribution. If uniform, the result will be uniform.
Double	b	Constant value for b.

Returns

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

Remarks

The outgoing message is the factor viewed as a function of a with difference integrated out. The formula is sum_difference p(difference) factor(difference,a,b).

Exceptions

Type	Condition
ImproperMessageException	Difference is not a proper distribution.

AAverageLogarithm(Double, Gaussian)

VMP message to a.

Declaration

[NotSupported("Variational Message Passing does not support a Minus factor with fixed output and two random inputs.")]
public static Gaussian AAverageLogarithm(double Difference, Gaussian b)

Parameters

Type	Name	Description
Double	Difference	Constant value for difference.
Gaussian	b	Incoming message from b. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except a. The formula is exp(sum_(b) p(b) log(factor(difference,a,b))).

Exceptions

Type	Condition
ImproperMessageException	b is not a proper distribution.

AAverageLogarithm(Double, Double)

VMP message to a.

Declaration

public static Gaussian AAverageLogarithm(double Difference, double b)

Parameters

Type	Name	Description
Double	Difference	Constant value for difference.
Double	b	Constant value for b.

Returns

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

Remarks

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

AverageLogFactor()

Evidence message for VMP.

Declaration

public static double AverageLogFactor()

Returns

Type	Description
Double	Zero.

Remarks

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

BAverageLogarithm(Gaussian, Gaussian)

VMP message to b.

Declaration

public static Gaussian BAverageLogarithm(Gaussian Difference, Gaussian a)

Parameters

Type	Name	Description
Gaussian	Difference	Incoming message from difference. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	a	Incoming message from a. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

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, difference is integrated out before taking the logarithm. The formula is exp(sum_(a) p(a) log(sum_difference p(difference) factor(difference,a,b))).

Exceptions

Type	Condition
ImproperMessageException	Difference is not a proper distribution.
ImproperMessageException	a is not a proper distribution.

BAverageLogarithm(Gaussian, Double)

VMP message to b.

Declaration

public static Gaussian BAverageLogarithm(Gaussian Difference, double a)

Parameters

Type	Name	Description
Gaussian	Difference	Incoming message from difference. Must be a proper distribution. If uniform, the result will be uniform.
Double	a	Constant value for a.

Returns

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

Remarks

The outgoing message is the factor viewed as a function of b with difference integrated out. The formula is sum_difference p(difference) factor(difference,a,b).

Exceptions

Type	Condition
ImproperMessageException	Difference is not a proper distribution.

BAverageLogarithm(Double, Gaussian)

VMP message to b.

Declaration

[NotSupported("Variational Message Passing does not support a Minus factor with fixed output and two random inputs.")]
public static Gaussian BAverageLogarithm(double Difference, Gaussian a)

Parameters

Type	Name	Description
Double	Difference	Constant value for difference.
Gaussian	a	Incoming message from a. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except b. The formula is exp(sum_(a) p(a) log(factor(difference,a,b))).

Exceptions

Type	Condition
ImproperMessageException	a is not a proper distribution.

BAverageLogarithm(Double, Double)

VMP message to b.

Declaration

public static Gaussian BAverageLogarithm(double Difference, double a)

Parameters

Type	Name	Description
Double	Difference	Constant value for difference.
Double	a	Constant value for a.

Returns

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

Remarks

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

DifferenceAverageLogarithm(Gaussian, Gaussian)

VMP message to difference.

Declaration

public static Gaussian DifferenceAverageLogarithm(Gaussian a, Gaussian b)

Parameters

Type	Name	Description
Gaussian	a	Incoming message from a. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	b	Incoming message from b. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	a is not a proper distribution.
ImproperMessageException	b is not a proper distribution.

DifferenceAverageLogarithm(Gaussian, Double)

VMP message to difference.

Declaration

public static Gaussian DifferenceAverageLogarithm(Gaussian a, double b)

Parameters

Type	Name	Description
Gaussian	a	Incoming message from a. Must be a proper distribution. If uniform, the result will be uniform.
Double	b	Constant value for b.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	a is not a proper distribution.

DifferenceAverageLogarithm(Double, Gaussian)

VMP message to difference.

Declaration

public static Gaussian DifferenceAverageLogarithm(double a, Gaussian b)

Parameters

Type	Name	Description
Double	a	Constant value for a.
Gaussian	b	Incoming message from b. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	b is not a proper distribution.

DifferenceAverageLogarithm(Double, Double)

VMP message to difference.

Declaration

public static Gaussian DifferenceAverageLogarithm(double a, double b)

Parameters

Type	Name	Description
Double	a	Constant value for a.
Double	b	Constant value for b.

Returns

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

Remarks

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