Class WishartFromShapeAndRateOp

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

Inheritance

Object

WishartFromShapeAndRateOp

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(Wishart), "SampleFromShapeAndRate", new Type[]{typeof(double), typeof(PositiveDefiniteMatrix)})]
[Quality(QualityBand.Stable)]
public static class WishartFromShapeAndRateOp

Methods

AverageLogFactor(Wishart, Double, Wishart)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Wishart sample, double shape, Wishart rate)

Parameters

Type	Name	Description
Wishart	sample	Incoming message from sample. Must be a proper distribution. If any element is uniform, the result will be uniform.
Double	shape	Constant value for shape.
Wishart	rate	Incoming message from rate. Must be a proper distribution. If any element is uniform, the result will be uniform.

Returns

Type	Description
Double	Average of the factor's log-value across the given argument distributions.

Remarks

The formula for the result is sum_(sample,rate) p(sample,rate) log(factor(sample,shape,rate)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Exceptions

Type	Condition
ImproperMessageException	sample is not a proper distribution.
ImproperMessageException	rate is not a proper distribution.

AverageLogFactor(PositiveDefiniteMatrix, Double, PositiveDefiniteMatrix)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(PositiveDefiniteMatrix sample, double shape, PositiveDefiniteMatrix rate)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	sample	Constant value for sample.
Double	shape	Constant value for shape.
PositiveDefiniteMatrix	rate	Constant value for rate.

Returns

Type	Description
Double	Average of the factor's log-value across the given argument distributions.

Remarks

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

LogAverageFactor(Wishart, Wishart)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Wishart sample, Wishart to_sample)

Parameters

Type	Name	Description
Wishart	sample	Incoming message from sample.
Wishart	to_sample	Outgoing message to sample.

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_(sample) p(sample) factor(sample,shape,rate)).

LogAverageFactor(PositiveDefiniteMatrix, Double, Wishart)

Evidence message for EP.

Declaration

public static double LogAverageFactor(PositiveDefiniteMatrix sample, double shape, Wishart rate)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	sample	Constant value for sample.
Double	shape	Constant value for shape.
Wishart	rate	Incoming message from rate.

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_(rate) p(rate) factor(sample,shape,rate)).

LogAverageFactor(PositiveDefiniteMatrix, Double, PositiveDefiniteMatrix)

Evidence message for EP.

Declaration

public static double LogAverageFactor(PositiveDefiniteMatrix sample, double shape, PositiveDefiniteMatrix rate)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	sample	Constant value for sample.
Double	shape	Constant value for shape.
PositiveDefiniteMatrix	rate	Constant value for rate.

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(sample,shape,rate)).

LogEvidenceRatio(Wishart, Double, PositiveDefiniteMatrix)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Wishart sample, double shape, PositiveDefiniteMatrix rate)

Parameters

Type	Name	Description
Wishart	sample	Incoming message from sample.
Double	shape	Constant value for shape.
PositiveDefiniteMatrix	rate	Constant value for rate.

Returns

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

Remarks

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

LogEvidenceRatio(PositiveDefiniteMatrix, Double, Wishart)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(PositiveDefiniteMatrix sample, double shape, Wishart rate)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	sample	Constant value for sample.
Double	shape	Constant value for shape.
Wishart	rate	Incoming message from rate.

Returns

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

Remarks

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

LogEvidenceRatio(PositiveDefiniteMatrix, Double, PositiveDefiniteMatrix)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(PositiveDefiniteMatrix sample, double shape, PositiveDefiniteMatrix rate)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	sample	Constant value for sample.
Double	shape	Constant value for shape.
PositiveDefiniteMatrix	rate	Constant value for rate.

Returns

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

Remarks

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

RateAverageConditional(PositiveDefiniteMatrix, Double, Wishart)

EP message to rate.

Declaration

public static Wishart RateAverageConditional(PositiveDefiniteMatrix sample, double shape, Wishart result)

Parameters

Type	Name	Description
PositiveDefiniteMatrix	sample	Constant value for sample.
Double	shape	Constant value for shape.
Wishart	result	Modified to contain the outgoing message.

Returns

Type	Description
Wishart	result

Remarks

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

RateAverageLogarithm(Wishart, Double, Wishart)

VMP message to rate.

Declaration

public static Wishart RateAverageLogarithm(Wishart sample, double shape, Wishart result)

Parameters

Type	Name	Description
Wishart	sample	Incoming message from sample. Must be a proper distribution. If any element is uniform, the result will be uniform.
Double	shape	Constant value for shape.
Wishart	result	Modified to contain the outgoing message.

Returns

Type	Description
Wishart	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	sample is not a proper distribution.

SampleAverageConditional(Double, PositiveDefiniteMatrix, Wishart)

EP message to sample.

Declaration

public static Wishart SampleAverageConditional(double shape, PositiveDefiniteMatrix rate, Wishart result)

Parameters

Type	Name	Description
Double	shape	Constant value for shape.
PositiveDefiniteMatrix	rate	Constant value for rate.
Wishart	result	Modified to contain the outgoing message.

Returns

Type	Description
Wishart	result

Remarks

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

SampleAverageLogarithm(Double, Wishart, Wishart)

VMP message to sample.

Declaration

public static Wishart SampleAverageLogarithm(double shape, Wishart rate, Wishart result)

Parameters

Type	Name	Description
Double	shape	Constant value for shape.
Wishart	rate	Incoming message from rate. Must be a proper distribution. If any element is uniform, the result will be uniform.
Wishart	result	Modified to contain the outgoing message.

Returns

Type	Description
Wishart	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	rate is not a proper distribution.

SampleAverageLogarithm(Double, PositiveDefiniteMatrix, Wishart)

VMP message to sample.

Declaration

public static Wishart SampleAverageLogarithm(double shape, PositiveDefiniteMatrix rate, Wishart result)

Parameters

Type	Name	Description
Double	shape	Constant value for shape.
PositiveDefiniteMatrix	rate	Constant value for rate.
Wishart	result	Modified to contain the outgoing message.

Returns

Type	Description
Wishart	result

Remarks

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