[FactorMethod(typeof(Gaussian), "Sample", new Type[]{typeof(double), typeof(double)}, Default = true)]
[FactorMethod(new string[]{"sample", "mean", "precision"}, typeof(Factor), "Gaussian", new Type[]{}, Default = true)]
[Quality(QualityBand.Mature)]
public class GaussianOp : GaussianOpBase

Fields

ForceProper

Static flag to force a proper distribution

Declaration

public static bool ForceProper

Field Value

Type	Description
Boolean

modified

Declaration

public static bool modified

Field Value

Type	Description
Boolean

QuadratureNodeCount

Number of quadrature nodes to use for computing the messages. Reduce this number to save time in exchange for less accuracy.

Declaration

public static int QuadratureNodeCount

Field Value

Type	Description
Int32

Methods

AverageLogFactor(Gaussian, Gaussian, Gamma)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Gaussian sample, Gaussian mean, Gamma precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If 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,mean,precision) p(sample,mean,precision) log(factor(sample,mean,precision)). 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	`mean` is not a proper distribution.
ImproperMessageException	`precision` is not a proper distribution.

AverageLogFactor(Gaussian, Gaussian, Double)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Gaussian sample, Gaussian mean, double precision)

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.
Double	precision	Constant value for `precision`.

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,mean) p(sample,mean) log(factor(sample,mean,precision)). 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	`mean` is not a proper distribution.

AverageLogFactor(Gaussian, Double, Gamma)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Gaussian sample, double mean, Gamma precision)

Parameters

Type	Name	Description
Gaussian	sample	Incoming message from `sample`. Must be a proper distribution. If uniform, the result will be uniform.
Double	mean	Constant value for `mean`.
Gamma	precision	Incoming message from `precision`. Must be a proper distribution. If 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,precision) p(sample,precision) log(factor(sample,mean,precision)). 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	`precision` is not a proper distribution.

AverageLogFactor(Gaussian, Double, Double)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Gaussian sample, double mean, double precision)

Parameters

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

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) p(sample) log(factor(sample,mean,precision)). 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.

AverageLogFactor(Double, Gaussian, Gamma)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(double sample, Gaussian mean, Gamma precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If 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_(mean,precision) p(mean,precision) log(factor(sample,mean,precision)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Exceptions

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

AverageLogFactor(Double, Gaussian, Double)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(double sample, Gaussian mean, double precision)

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.
Double	precision	Constant value for `precision`.

Returns

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

Remarks

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

Exceptions

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

AverageLogFactor(Double, Double, Gamma)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(double sample, double mean, Gamma precision)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Double	mean	Constant value for `mean`.
Gamma	precision	Incoming message from `precision`. Must be a proper distribution. If 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_(precision) p(precision) log(factor(sample,mean,precision)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Exceptions

Type	Condition
ImproperMessageException	`precision` is not a proper distribution.

AverageLogFactor(Double, Double, Double)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(double sample, double mean, double precision)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Double	mean	Constant value for `mean`.
Double	precision	Constant value for `precision`.

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,mean,precision)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

GammaFromAlphaBeta(Gamma, Double, Double, Boolean)

Gamma message computed directly from prior and expected derivatives of factor

Declaration

public static Gamma GammaFromAlphaBeta(Gamma prior, double alpha, double beta, bool forceProper)

Parameters

Type	Name	Description
Gamma	prior
Double	alpha	Exf'/Ef = -b dlogZ/db
Double	beta	(Exf' + Ex^2f'')/Ef - alpha^2 = -b dalpha/db
Boolean	forceProper

Returns

Type	Description
Gamma

GaussianFromAlphaBeta(Gaussian, Double, Double, Boolean)

Compute an EP message

Declaration

public static Gaussian GaussianFromAlphaBeta(Gaussian prior, double alpha, double beta, bool forceProper)

Parameters

Type	Name	Description
Gaussian	prior
Double	alpha	dlogZ/dm0
Double	beta	ddlogZ/dm0^2
Boolean	forceProper

Returns

Type	Description
Gaussian

LogAverageFactor(Gaussian, Gaussian, Gamma, Gamma)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Gaussian sample, Gaussian mean, Gamma precision, Gamma to_precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	to_precision	Previous outgoing message to `precision`.

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,mean,precision) p(sample,mean,precision) factor(sample,mean,precision)).

Exceptions

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

LogAverageFactor(Gaussian, Double, Gamma, Gamma)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Gaussian sample, double mean, Gamma precision, Gamma to_precision)

Parameters

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

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,precision) p(sample,precision) factor(sample,mean,precision)).

Exceptions

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

LogAverageFactor(Double, Gaussian, Gamma, Gamma)

Evidence message for EP.

Declaration

public static double LogAverageFactor(double sample, Gaussian mean, Gamma precision, Gamma to_precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	to_precision	Previous outgoing message to `precision`.

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_(mean,precision) p(mean,precision) factor(sample,mean,precision)).

Exceptions

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

LogAverageFactor_slow(Gaussian, Gaussian, Gamma)

Declaration

public static double LogAverageFactor_slow(Gaussian sample, Gaussian mean, Gamma precision)

Parameters

Type	Name	Description
Gaussian	sample
Gaussian	mean
Gamma	precision

Returns

Type	Description
Double

LogEvidenceRatio(Gaussian, Gaussian, Gamma, Gaussian, Gamma)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Gaussian sample, Gaussian mean, Gamma precision, Gaussian to_sample, Gamma to_precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_sample	Outgoing message to `sample`.
Gamma	to_precision	Previous outgoing message to `precision`.

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,precision) p(sample,mean,precision) factor(sample,mean,precision) / 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	`precision` is not a proper distribution.

LogEvidenceRatio(Gaussian, Double, Gamma, Gaussian, Gamma)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Gaussian sample, double mean, Gamma precision, Gaussian to_sample, Gamma to_precision)

Parameters

Type	Name	Description
Gaussian	sample	Incoming message from `sample`. Must be a proper distribution. If uniform, the result will be uniform.
Double	mean	Constant value for `mean`.
Gamma	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_sample	Outgoing message to `sample`.
Gamma	to_precision	Previous outgoing message to `precision`.

Returns

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

Remarks

The formula for the result is log(sum_(sample,precision) p(sample,precision) factor(sample,mean,precision) / 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	`precision` is not a proper distribution.

LogEvidenceRatio(Double, Gaussian, Gamma, Gamma)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(double sample, Gaussian mean, Gamma precision, Gamma to_precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	to_precision	Previous outgoing message to `precision`.

Returns

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

Remarks

The formula for the result is log(sum_(mean,precision) p(mean,precision) factor(sample,mean,precision)). 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	`precision` is not a proper distribution.

LogFactorValue(Double, Double, Double)

Evidence message for Gibbs.

Declaration

public static double LogFactorValue(double sample, double mean, double precision)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Double	mean	Constant value for `mean`.
Double	precision	Constant value for `precision`.

Returns

Type	Description
Double	Logarithm of the factor's value at the given arguments.

Remarks

MeanAverageConditional(Gaussian, Gaussian, Gamma, Gamma)

EP message to mean.

Declaration

public static Gaussian MeanAverageConditional(Gaussian sample, Gaussian mean, Gamma precision, Gamma to_precision)

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`.
Gamma	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	to_precision	Previous outgoing message to `precision`.

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,precision) p(sample,precision) factor(sample,mean,precision)]/p(mean).

Exceptions

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

MeanAverageConditional(Double, Gaussian, Gamma, Gamma)

EP message to mean.

Declaration

public static Gaussian MeanAverageConditional(double sample, Gaussian mean, Gamma precision, Gamma to_precision)

Parameters

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

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_(precision) p(precision) factor(sample,mean,precision)]/p(mean).

Exceptions

Type	Condition
ImproperMessageException	`precision` is not a proper distribution.

MeanAverageConditional(Double, Double, TruncatedGaussian)

EP message to mean.

Declaration

public static TruncatedGaussian MeanAverageConditional(double sample, double precision, TruncatedGaussian result)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Double	precision	Constant value for `precision`.
TruncatedGaussian	result	Modified to contain the outgoing message.

Returns

Type	Description
TruncatedGaussian	`result`

Remarks

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

MeanAverageConditional_slow(Gaussian, Gaussian, Gamma)

Declaration

public static Gaussian MeanAverageConditional_slow(Gaussian sample, Gaussian mean, Gamma precision)

Parameters

Type	Name	Description
Gaussian	sample
Gaussian	mean
Gamma	precision

Returns

Type	Description
Gaussian

MeanAverageLogarithm(Gaussian, Gamma)

VMP message to mean.

Declaration

public static Gaussian MeanAverageLogarithm(Gaussian sample, Gamma precision)

Parameters

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

Returns

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

Remarks

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

Exceptions

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

MeanAverageLogarithm(Gaussian, Double)

VMP message to mean.

Declaration

public static Gaussian MeanAverageLogarithm(Gaussian sample, double precision)

Parameters

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

Returns

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

Remarks

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

Exceptions

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

MeanAverageLogarithm(Double, Gamma)

VMP message to mean.

Declaration

public static Gaussian MeanAverageLogarithm(double sample, Gamma precision)

Parameters

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

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	`precision` is not a proper distribution.

MeanAverageLogarithm(Double, Double)

VMP message to mean.

Declaration

public static Gaussian MeanAverageLogarithm(double sample, double precision)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Double	precision	Constant value for `precision`.

Returns

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

Remarks

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

PrecisionAverageConditional(Gaussian, Gaussian, Gamma)

EP message to precision.

Declaration

public static Gamma PrecisionAverageConditional(Gaussian sample, Gaussian mean, Gamma precision)

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	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.

Returns

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

Remarks

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

Exceptions

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

PrecisionAverageConditional_Point(Double, Double, Double)

Declaration

public static Gamma PrecisionAverageConditional_Point(double ym, double yv, double precision)

Parameters

Type	Name	Description
Double	ym
Double	yv
Double	precision

Returns

Type	Description
Gamma

PrecisionAverageConditional_slow(Gaussian, Gaussian, Gamma)

Declaration

public static Gamma PrecisionAverageConditional_slow(Gaussian sample, Gaussian mean, Gamma precision)

Parameters

Type	Name	Description
Gaussian	sample
Gaussian	mean
Gamma	precision

Returns

Type	Description
Gamma

PrecisionAverageLogarithm(Gaussian, Gaussian)

VMP message to precision.

Declaration

public static Gamma PrecisionAverageLogarithm(Gaussian sample, Gaussian mean)

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.

Returns

Type	Description
Gamma	The outgoing VMP message to the `precision` argument.

Remarks

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

Exceptions

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

PrecisionAverageLogarithm(Gaussian, Double)

VMP message to precision.

Declaration

public static Gamma PrecisionAverageLogarithm(Gaussian sample, double mean)

Parameters

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

Returns

Type	Description
Gamma	The outgoing VMP message to the `precision` argument.

Remarks

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

Exceptions

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

PrecisionAverageLogarithm(Double, Gaussian)

VMP message to precision.

Declaration

public static Gamma PrecisionAverageLogarithm(double sample, Gaussian mean)

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.

Returns

Type	Description
Gamma	The outgoing VMP message to the `precision` argument.

Remarks

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

Exceptions

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

PrecisionAverageLogarithm(Double, Double)

VMP message to precision.

Declaration

public static Gamma PrecisionAverageLogarithm(double sample, double mean)

Parameters

Type	Name	Description
Double	sample	Constant value for `sample`.
Double	mean	Constant value for `mean`.

Returns

Type	Description
Gamma	The outgoing VMP message to the `precision` argument.

Remarks

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

QuadratureNodesAndWeights(Gamma, Double[], Double[])

Quadrature nodes for Gamma expectations

Declaration

public static void QuadratureNodesAndWeights(Gamma precision, double[] nodes, double[] logWeights)

Parameters

Type	Name	Description
Gamma	precision	'precision' message
Double[]	nodes	Place to put the nodes
Double[]	logWeights	Place to put the log-weights

SampleAverageConditional(Gaussian, Gaussian, Gamma, Gamma)

EP message to sample.

Declaration

public static Gaussian SampleAverageConditional(Gaussian sample, Gaussian mean, Gamma precision, Gamma to_precision)

Parameters

Type	Name	Description
Gaussian	sample	Incoming message from `sample`.
Gaussian	mean	Incoming message from `mean`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	precision	Incoming message from `precision`. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	to_precision	Previous outgoing message to `precision`.

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,precision) p(mean,precision) factor(sample,mean,precision)]/p(sample).

Exceptions

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

SampleAverageConditional(Gaussian, Double, Gamma, Gamma)

EP message to sample.

Declaration

public static Gaussian SampleAverageConditional(Gaussian sample, double mean, Gamma precision, Gamma to_precision)

Parameters

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

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_(precision) p(precision) factor(sample,mean,precision)]/p(sample).

Exceptions

Type	Condition
ImproperMessageException	`precision` is not a proper distribution.

SampleAverageConditional(Double, Double, TruncatedGaussian)

EP message to sample.

Declaration

public static TruncatedGaussian SampleAverageConditional(double mean, double precision, TruncatedGaussian result)

Parameters

Type	Name	Description
Double	mean	Constant value for `mean`.
Double	precision	Constant value for `precision`.
TruncatedGaussian	result	Modified to contain the outgoing message.

Returns

Type	Description
TruncatedGaussian	`result`

Remarks

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

SampleAverageConditional_slow(Gaussian, Gaussian, Gamma)

Declaration

public static Gaussian SampleAverageConditional_slow(Gaussian sample, Gaussian mean, Gamma precision)

Parameters

Type	Name	Description
Gaussian	sample
Gaussian	mean
Gamma	precision

Returns

Type	Description
Gaussian

SampleAverageConditionalInit()

Declaration

public static Gaussian SampleAverageConditionalInit()

Returns

Type	Description
Gaussian

Remarks

SampleAverageLogarithm(Gaussian, Gamma)

VMP message to sample.

Declaration

public static Gaussian SampleAverageLogarithm(Gaussian mean, Gamma precision)

Parameters

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

Returns

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

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_(mean,precision) p(mean,precision) log(factor(sample,mean,precision))).

Exceptions

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

SampleAverageLogarithm(Gaussian, Double)

VMP message to sample.

Declaration

public static Gaussian SampleAverageLogarithm(Gaussian mean, double precision)

Parameters

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

Returns

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

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_(mean) p(mean) log(factor(sample,mean,precision))).

Exceptions

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

SampleAverageLogarithm(Double, Gamma)

VMP message to sample.

Declaration

public static Gaussian SampleAverageLogarithm(double mean, Gamma precision)

Parameters

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

Returns

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

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_(precision) p(precision) log(factor(sample,mean,precision))).

Exceptions

Type	Condition
ImproperMessageException	`precision` is not a proper distribution.

SampleAverageLogarithm(Double, Double)

VMP message to sample.

Declaration

public static Gaussian SampleAverageLogarithm(double mean, double precision)

Parameters

Type	Name	Description
Double	mean	Constant value for `mean`.
Double	precision	Constant value for `precision`.

Returns

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

Remarks

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