Class CasesBoolOp

Provides outgoing messages for CasesBool(Boolean, out Boolean, out Boolean), given random arguments to the function.

Inheritance

Object

CasesBoolOp

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(Gate), "CasesBool", new Type[]{typeof(bool), typeof(bool), typeof(bool)})]
[Quality(QualityBand.Experimental)]
public static class CasesBoolOp

Methods

AverageLogFactor(Bernoulli, Bernoulli, Bernoulli)

Evidence message for VMP.

Declaration

[SkipIfAllUniform(new string[]{"case0", "case1"})]
public static double AverageLogFactor(Bernoulli case0, Bernoulli case1, Bernoulli b)

Parameters

Type	Name	Description
Bernoulli	case0	Incoming message from `case0`.
Bernoulli	case1	Incoming message from `case1`.
Bernoulli	b	Incoming message from `b`.

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.

BAverageConditional(Bernoulli, Bernoulli)

EP message to b.

Declaration

[SkipIfAllUniform]
public static Bernoulli BAverageConditional(Bernoulli case0, Bernoulli case1)

Parameters

Type	Name	Description
Bernoulli	case0	Incoming message from `case0`.
Bernoulli	case1	Incoming message from `case1`.

Returns

Type	Description
Bernoulli	The outgoing EP message to the `b` argument.

Remarks

The outgoing message is a distribution matching the moments of b as the random arguments are varied. The formula is proj[p(b) sum_(case0,case1) p(case0,case1) factor(b,case0,case1)]/p(b).

BAverageLogarithm(Bernoulli, Bernoulli)

VMP message to b.

Declaration

[SkipIfAllUniform]
public static Bernoulli BAverageLogarithm(Bernoulli case0, Bernoulli case1)

Parameters

Type	Name	Description
Bernoulli	case0	Incoming message from `case0`.
Bernoulli	case1	Incoming message from `case1`.

Returns

Type	Description
Bernoulli	The outgoing VMP message to the `b` argument.

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except b. The formula is exp(sum_(case0,case1) p(case0,case1) log(factor(b,case0,case1))).

Case0AverageConditional(Bernoulli)

EP message to case0.

Declaration

public static Bernoulli Case0AverageConditional(Bernoulli b)

Parameters

Type	Name	Description
Bernoulli	b	Incoming message from `b`.

Returns

Type	Description
Bernoulli	The outgoing EP message to the `case0` argument.

Remarks

The outgoing message is a distribution matching the moments of case0 as the random arguments are varied. The formula is proj[p(case0) sum_(b) p(b) factor(b,case0,case1)]/p(case0).

Case0AverageLogarithm(Bernoulli)

VMP message to case0.

Declaration

public static Bernoulli Case0AverageLogarithm(Bernoulli b)

Parameters

Type	Name	Description
Bernoulli	b	Incoming message from `b`.

Returns

Type	Description
Bernoulli	The outgoing VMP message to the `case0` argument.

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except case0. The formula is exp(sum_(b) p(b) log(factor(b,case0,case1))).

Case1AverageConditional(Bernoulli)

EP message to case1.

Declaration

public static Bernoulli Case1AverageConditional(Bernoulli b)

Parameters

Type	Name	Description
Bernoulli	b	Incoming message from `b`.

Returns

Type	Description
Bernoulli	The outgoing EP message to the `case1` argument.

Remarks

The outgoing message is a distribution matching the moments of case1 as the random arguments are varied. The formula is proj[p(case1) sum_(b) p(b) factor(b,case0,case1)]/p(case1).

Case1AverageLogarithm(Bernoulli)

VMP message to case1.

Declaration

public static Bernoulli Case1AverageLogarithm(Bernoulli b)

Parameters

Type	Name	Description
Bernoulli	b	Incoming message from `b`.

Returns

Type	Description
Bernoulli	The outgoing VMP message to the `case1` argument.

Remarks

The outgoing message is the exponential of the average log-factor value, where the average is over all arguments except case1. The formula is exp(sum_(b) p(b) log(factor(b,case0,case1))).

LogEvidenceRatio(Bernoulli, Bernoulli, Bernoulli)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Bernoulli case0, Bernoulli case1, Bernoulli b)

Parameters

Type	Name	Description
Bernoulli	case0	Incoming message from `case0`.
Bernoulli	case1	Incoming message from `case1`.
Bernoulli	b	Incoming message from `b`.

Returns

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

Remarks

The formula for the result is log(sum_(case0,case1,b) p(case0,case1,b) factor(b,case0,case1)). Adding up these values across all factors and variables gives the log-evidence estimate for EP.