Class GaussianFromMeanAndVarianceOp_PointVariance

This class defines specializations for the case where variance is a point mass. These methods have fewer inputs, allowing more efficient schedules.

Inheritance

Object

GaussianFromMeanAndVarianceOp_PointVariance

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), "GaussianFromMeanAndVariance", new Type[]{}, Default = false)]
[Quality(QualityBand.Preview)]
public static class GaussianFromMeanAndVarianceOp_PointVariance

Methods

LogEvidenceRatio(Gaussian, Gaussian, Gamma)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Gaussian sample, Gaussian mean, Gamma variance)

Parameters

Type	Name	Description
Gaussian	sample	Incoming message from `sample`. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	mean	Incoming message from `mean`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	variance	Incoming message from `variance`. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	`sample` is not a proper distribution.
ImproperMessageException	`mean` is not a proper distribution.
ImproperMessageException	`variance` is not a proper distribution.

LogEvidenceRatio(Double, Gaussian, Gamma)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(double sample, Gaussian mean, Gamma variance)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Gaussian	mean	Incoming message from `mean`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	variance	Incoming message from `variance`. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	`mean` is not a proper distribution.
ImproperMessageException	`variance` is not a proper distribution.

MeanAverageConditional(Gaussian, Gamma)

EP message to mean.

Declaration

public static Gaussian MeanAverageConditional(Gaussian sample, Gamma variance)

Parameters

Type	Name	Description
Gaussian	sample	Incoming message from `sample`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	variance	Incoming message from `variance`. Must be a proper distribution. If uniform, the result will be uniform.

Returns

Type	Description
Gaussian	The outgoing EP message to the `mean` argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	`sample` is not a proper distribution.
ImproperMessageException	`variance` is not a proper distribution.

SampleAverageConditional(Gaussian, Gamma)

EP message to sample.

Declaration

public static Gaussian SampleAverageConditional(Gaussian mean, Gamma variance)

Parameters

Type	Name	Description
Gaussian	mean	Incoming message from `mean`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	variance	Incoming message from `variance`. Must be a proper distribution. If uniform, the result will be uniform.

Returns

Type	Description
Gaussian	The outgoing EP message to the `sample` argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	`mean` is not a proper distribution.
ImproperMessageException	`variance` is not a proper distribution.

VarianceAverageConditional(Gaussian, Gaussian, Gamma)

EP message to variance.

Declaration

public static Gamma VarianceAverageConditional(Gaussian sample, Gaussian mean, Gamma variance)

Parameters

Type	Name	Description
Gaussian	sample	Incoming message from `sample`. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	mean	Incoming message from `mean`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	variance	Incoming message from `variance`. Must be a proper distribution. If uniform, the result will be uniform.

Returns

Type	Description
Gamma	The outgoing EP message to the `variance` argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	`sample` is not a proper distribution.
ImproperMessageException	`mean` is not a proper distribution.
ImproperMessageException	`variance` is not a proper distribution.