Class IsPositiveOp

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

Inheritance

Object

IsPositiveOp

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), "IsPositive", new Type[]{typeof(double)})]
[Quality(QualityBand.Mature)]
public static class IsPositiveOp

Methods

AverageLogFactor(Bernoulli, Gaussian, Gaussian)

Evidence message for VMP.

Declaration

[Quality(QualityBand.Preview)]
public static double AverageLogFactor(Bernoulli isPositive, Gaussian X, Gaussian to_X)

Parameters

Type	Name	Description
Bernoulli	isPositive	Incoming message from isPositive.
Gaussian	X	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_X	Previous outgoing message to X.

Returns

Type	Description
Double	Zero.

Remarks

In Variational Message Passing, the evidence contribution of a deterministic factor is zero. Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Exceptions

Type	Condition
ImproperMessageException	X is not a proper distribution.

AverageLogFactor(TruncatedGaussian)

Evidence message for VMP.

Declaration

[Quality(QualityBand.Preview)]
public static double AverageLogFactor(TruncatedGaussian X)

Parameters

Type	Name	Description
TruncatedGaussian	X	Incoming message from x.

Returns

Type	Description
Double	Zero.

Remarks

In Variational Message Passing, the evidence contribution of a deterministic factor is zero. Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

AverageLogFactor(Boolean, Gaussian, Gaussian)

Evidence message for VMP.

Declaration

[Quality(QualityBand.Preview)]
public static double AverageLogFactor(bool isPositive, Gaussian x, Gaussian to_X)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Gaussian	x	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_X	Previous outgoing message to X.

Returns

Type	Description
Double	Zero.

Remarks

In Variational Message Passing, the evidence contribution of a deterministic factor is zero. Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

AverageLogFactor(Boolean, Double)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(bool isPositive, double x)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Double	x	Constant value for x.

Returns

Type	Description
Double	Zero.

Remarks

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

AverageLogFactor_helper(Gaussian, Gaussian)

Evidence message for VMP

Declaration

[Quality(QualityBand.Preview)]
public static double AverageLogFactor_helper(Gaussian X, Gaussian to_X)

Parameters

Type	Name	Description
Gaussian	X	Incoming message from 'x'. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_X	Previous outgoing message to 'X'.

Returns

Type	Description
Double	Zero

Remarks

In Variational Message Passing, the evidence contribution of a deterministic factor is zero. Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

Exceptions

Type	Condition
ImproperMessageException	X is not a proper distribution

IsPositiveAverageConditional(Gaussian)

EP message to isPositive.

Declaration

public static Bernoulli IsPositiveAverageConditional(Gaussian x)

Parameters

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

Returns

Type	Description
Bernoulli	The outgoing EP message to the isPositive argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

IsPositiveAverageConditionalInit()

Declaration

public static Bernoulli IsPositiveAverageConditionalInit()

Returns

Type	Description
Bernoulli

Remarks

IsPositiveAverageLogarithm(Gaussian)

VMP message to isPositive.

Declaration

[Quality(QualityBand.Preview)]
public static Bernoulli IsPositiveAverageLogarithm(Gaussian x)

Parameters

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

Returns

Type	Description
Bernoulli	The outgoing VMP message to the isPositive argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

LogAverageFactor(Bernoulli, Gaussian)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Bernoulli isPositive, Gaussian x)

Parameters

Type	Name	Description
Bernoulli	isPositive	Incoming message from isPositive.
Gaussian	x	Incoming message from x.

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_(isPositive,x) p(isPositive,x) factor(isPositive,x)).

LogAverageFactor(Boolean, Gaussian)

Evidence message for EP.

Declaration

public static double LogAverageFactor(bool isPositive, Gaussian x)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Gaussian	x	Incoming message from x.

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_(x) p(x) factor(isPositive,x)).

LogAverageFactor(Boolean, Double)

Evidence message for EP.

Declaration

public static double LogAverageFactor(bool isPositive, double x)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Double	x	Constant value for x.

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(isPositive,x)).

LogEvidenceRatio(Bernoulli, Gaussian)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Bernoulli isPositive, Gaussian x)

Parameters

Type	Name	Description
Bernoulli	isPositive	Incoming message from isPositive.
Gaussian	x	Incoming message from x.

Returns

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

Remarks

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

LogEvidenceRatio(Boolean, Gaussian)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(bool isPositive, Gaussian x)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Gaussian	x	Incoming message from x.

Returns

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

Remarks

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

LogEvidenceRatio(Boolean, Double)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(bool isPositive, double x)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Double	x	Constant value for x.

Returns

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

Remarks

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

XAverageConditional(Bernoulli)

EP message to x.

Declaration

[Quality(QualityBand.Preview)]
public static TruncatedGaussian XAverageConditional(Bernoulli isPositive)

Parameters

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

Returns

Type	Description
TruncatedGaussian	The outgoing EP message to the x argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	isPositive is not a proper distribution.

XAverageConditional(Bernoulli, Gaussian)

EP message to x.

Declaration

public static Gaussian XAverageConditional(Bernoulli isPositive, Gaussian x)

Parameters

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

Returns

Type	Description
Gaussian	The outgoing EP message to the x argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	isPositive is not a proper distribution.
ImproperMessageException	x is not a proper distribution.

XAverageConditional(Bernoulli, Double)

EP message to x.

Declaration

public static Gaussian XAverageConditional(Bernoulli isPositive, double x)

Parameters

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

Returns

Type	Description
Gaussian	The outgoing EP message to the x argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	isPositive is not a proper distribution.

XAverageConditional(Boolean)

EP message to x.

Declaration

[Quality(QualityBand.Preview)]
public static TruncatedGaussian XAverageConditional(bool isPositive)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.

Returns

Type	Description
TruncatedGaussian	The outgoing EP message to the x argument.

Remarks

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

XAverageConditional(Boolean, Gaussian)

EP message to x.

Declaration

public static Gaussian XAverageConditional(bool isPositive, Gaussian x)

Parameters

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

Returns

Type	Description
Gaussian	The outgoing EP message to the x argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

XAverageConditional_Helper(Bernoulli, Gaussian, Boolean)

Declaration

public static Gaussian XAverageConditional_Helper(Bernoulli isPositive, Gaussian x, bool forceProper)

Parameters

Type	Name	Description
Bernoulli	isPositive
Gaussian	x
Boolean	forceProper

Returns

Type	Description
Gaussian

XAverageConditionalInit()

Declaration

public static Gaussian XAverageConditionalInit()

Returns

Type	Description
Gaussian

Remarks

XAverageLogarithm(Bernoulli, Gaussian, Gaussian)

VMP message to x.

Declaration

[Quality(QualityBand.Preview)]
public static Gaussian XAverageLogarithm(Bernoulli isPositive, Gaussian x, Gaussian to_X)

Parameters

Type	Name	Description
Bernoulli	isPositive	Incoming message from isPositive. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	x	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_X	Previous outgoing message to X.

Returns

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

Remarks

The outgoing message is the factor viewed as a function of x with isPositive integrated out. The formula is sum_isPositive p(isPositive) factor(isPositive,x).

Exceptions

Type	Condition
ImproperMessageException	isPositive is not a proper distribution.
ImproperMessageException	x is not a proper distribution.

XAverageLogarithm(Boolean)

VMP message to x.

Declaration

[Quality(QualityBand.Preview)]
public static TruncatedGaussian XAverageLogarithm(bool isPositive)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.

Returns

Type	Description
TruncatedGaussian	The outgoing VMP message to the x argument.

Remarks

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

XAverageLogarithm(Boolean, Gaussian, Gaussian)

VMP message to x.

Declaration

[Quality(QualityBand.Preview)]
public static Gaussian XAverageLogarithm(bool isPositive, Gaussian x, Gaussian to_X)

Parameters

Type	Name	Description
Boolean	isPositive	Constant value for isPositive.
Gaussian	x	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Gaussian	to_X	Previous outgoing message to X.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.