Class PowerPlateOp

Provides outgoing messages for Enter<T>(T, Double), given random arguments to the function.

Inheritance

Object

PowerPlateOp

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(PowerPlate), "Enter<>", new Type[]{})]
[Quality(QualityBand.Preview)]
public static class PowerPlateOp

Methods

AverageLogFactor()

Evidence message for VMP.

Declaration

public static double AverageLogFactor()

Returns

Type	Description
Double	Zero.

Remarks

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

EnterAverageConditional<T>(T, T, Double, T)

EP message to enter.

Declaration

[SkipIfAllUniform(new string[]{"enter", "value"})]
public static T EnterAverageConditional<T>(T enter, T value, double exponent, T result)
    where T : SettableToPower<T>, SettableToProduct<T>

Parameters

Type	Name	Description
T	enter	Incoming message from enter.
T	value	Incoming message from value.
Double	exponent	Constant value for exponent.
T	result	Modified to contain the outgoing message.

Returns

Type	Description
T	result

Type Parameters

Name	Description
T	The type of the distribution over the variable entering the power plate.

Remarks

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

EnterAverageConditionalInit<T>(T)

Declaration

public static T EnterAverageConditionalInit<T>(T value)
    where T : ICloneable

Parameters

Type	Name	Description
T	value	Incoming message from value.

Returns

Type	Description
T

Type Parameters

Name	Description
T	The type of the distribution over the variable entering the power plate.

Remarks

EnterAverageLogarithm<T>(T)

VMP message to enter.

Declaration

public static T EnterAverageLogarithm<T>(T value)

Parameters

Type	Name	Description
T	value	Incoming message from value.

Returns

Type	Description
T	The outgoing VMP message to the enter argument.

Type Parameters

Name	Description
T	The type of the distribution over the variable entering the power plate.

Remarks

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

LogEvidenceRatio<T>(T, T, Double, T)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio<T>(T enter, T value, double exponent, T to_enter)
    where T : CanGetLogAverageOf<T>, CanGetLogAverageOfPower<T>

Parameters

Type	Name	Description
T	enter	Incoming message from enter.
T	value	Incoming message from value.
Double	exponent	Constant value for exponent.
T	to_enter	Outgoing message to enter.

Returns

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

Type Parameters

Name	Description
T	The type of the distribution over the variable entering the power plate.

Remarks

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

ValueAverageConditional<T>(T, Double, T)

EP message to value.

Declaration

public static T ValueAverageConditional<T>(T enter, double exponent, T result)
    where T : SettableToPower<T>

Parameters

Type	Name	Description
T	enter	Incoming message from enter. Must be a proper distribution. If uniform, the result will be uniform.
Double	exponent	Constant value for exponent.
T	result	Modified to contain the outgoing message.

Returns

Type	Description
T	result

Type Parameters

Name	Description
T	The type of the distribution over the variable entering the power plate.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	enter is not a proper distribution.

ValueAverageLogarithm<T>(T, Double, T)

VMP message to value.

Declaration

public static T ValueAverageLogarithm<T>(T enter, double exponent, T result)
    where T : SettableToPower<T>

Parameters

Type	Name	Description
T	enter	Incoming message from enter. Must be a proper distribution. If uniform, the result will be uniform.
Double	exponent	Constant value for exponent.
T	result	Modified to contain the outgoing message.

Returns

Type	Description
T	result

Type Parameters

Name	Description
T	The type of the distribution over the variable entering the power plate.

Remarks

The outgoing message is the factor viewed as a function of value with enter integrated out. The formula is sum_enter p(enter) factor(enter,value,exponent).

Exceptions

Type	Condition
ImproperMessageException	enter is not a proper distribution.