Class PowerOp

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

Inheritance

Object

PowerOp

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(Math), "Pow", new Type[]{typeof(double), typeof(double)})]
[Quality(QualityBand.Experimental)]
public static class PowerOp

Methods

FromMeanPowerAndMeanLog(Double, Double, Double)

Declaration

public static Gamma FromMeanPowerAndMeanLog(double meanPower, double meanLog, double power)

Parameters

Type	Name	Description
Double	meanPower
Double	meanLog
Double	power

Returns

Type	Description
Gamma

GammaFromGammaPower(GammaPower)

Declaration

public static Gamma GammaFromGammaPower(GammaPower message)

Parameters

Type	Name	Description
GammaPower	message

Returns

Type	Description
Gamma

GammaFromMeanAndMeanInverse(Double, Double)

Declaration

public static Gamma GammaFromMeanAndMeanInverse(double mean, double meanInverse)

Parameters

Type	Name	Description
Double	mean
Double	meanInverse

Returns

Type	Description
Gamma

GammaPowerFromDifferentPower(GammaPower, Double)

Declaration

public static GammaPower GammaPowerFromDifferentPower(GammaPower message, double newPower)

Parameters

Type	Name	Description
GammaPower	message
Double	newPower

Returns

Type	Description
GammaPower

LogAverageFactor(GammaPower, GammaPower, Double)

Evidence message for EP.

Declaration

public static double LogAverageFactor(GammaPower pow, GammaPower x, double y)

Parameters

Type	Name	Description
GammaPower	pow	Incoming message from pow.
GammaPower	x	Incoming message from x.
Double	y	Constant value for y.

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_(pow,x) p(pow,x) factor(pow,x,y)).

PowAverageConditional(Gamma, Double)

EP message to pow.

Declaration

public static GammaPower PowAverageConditional(Gamma x, double y)

Parameters

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

Returns

Type	Description
GammaPower	The outgoing EP message to the pow argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

PowAverageConditional(Gamma, Double, Gamma)

EP message to pow.

Declaration

public static Gamma PowAverageConditional(Gamma x, double y, Gamma result)

Parameters

Type	Name	Description
Gamma	x	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Double	y	Constant value for y.
Gamma	result	Modified to contain the outgoing message.

Returns

Type	Description
Gamma	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

PowAverageConditional(GammaPower, Double, GammaPower)

EP message to pow.

Declaration

public static GammaPower PowAverageConditional(GammaPower x, double y, GammaPower result)

Parameters

Type	Name	Description
GammaPower	x	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Double	y	Constant value for y.
GammaPower	result	Modified to contain the outgoing message.

Returns

Type	Description
GammaPower	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

PowAverageConditional(Pareto, Double)

EP message to pow.

Declaration

public static Pareto PowAverageConditional(Pareto x, double y)

Parameters

Type	Name	Description
Pareto	x	Incoming message from x.
Double	y	Constant value for y.

Returns

Type	Description
Pareto	The outgoing EP message to the pow argument.

Remarks

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

PowAverageConditional(TruncatedGamma, Double)

EP message to pow.

Declaration

public static Gamma PowAverageConditional(TruncatedGamma x, double y)

Parameters

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

Returns

Type	Description
Gamma	The outgoing EP message to the pow argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

PowAverageConditional(TruncatedGamma, Double, GammaPower)

Declaration

public static GammaPower PowAverageConditional(TruncatedGamma x, double y, GammaPower result)

Parameters

Type	Name	Description
TruncatedGamma	x
Double	y
GammaPower	result

Returns

Type	Description
GammaPower

PowAverageLogarithm(Gamma, Double)

VMP message to pow.

Declaration

public static GammaPower PowAverageLogarithm(Gamma x, double y)

Parameters

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

Returns

Type	Description
GammaPower	The outgoing VMP message to the pow argument.

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

PowAverageLogarithm(GammaPower, Double, GammaPower)

VMP message to pow.

Declaration

public static GammaPower PowAverageLogarithm(GammaPower x, double y, GammaPower result)

Parameters

Type	Name	Description
GammaPower	x	Incoming message from x. Must be a proper distribution. If uniform, the result will be uniform.
Double	y	Constant value for y.
GammaPower	result	Modified to contain the outgoing message.

Returns

Type	Description
GammaPower	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	x is not a proper distribution.

XAverageConditional(Gamma, Gamma, Double, Gamma)

EP message to x.

Declaration

public static Gamma XAverageConditional(Gamma pow, Gamma x, double y, Gamma result)

Parameters

Type	Name	Description
Gamma	pow	Incoming message from pow. Must be a proper distribution. If uniform, the result will be uniform.
Gamma	x	Incoming message from x.
Double	y	Constant value for y.
Gamma	result	Modified to contain the outgoing message.

Returns

Type	Description
Gamma	result

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_(pow) p(pow) factor(pow,x,y)]/p(x).

Exceptions

Type	Condition
ImproperMessageException	pow is not a proper distribution.

XAverageConditional(Gamma, TruncatedGamma, Double)

Declaration

public static TruncatedGamma XAverageConditional(Gamma pow, TruncatedGamma x, double y)

Parameters

Type	Name	Description
Gamma	pow
TruncatedGamma	x
Double	y

Returns

Type	Description
TruncatedGamma

XAverageConditional(GammaPower, GammaPower, Double, GammaPower)

EP message to x.

Declaration

public static GammaPower XAverageConditional(GammaPower pow, GammaPower x, double y, GammaPower result)

Parameters

Type	Name	Description
GammaPower	pow	Incoming message from pow. Must be a proper distribution. If uniform, the result will be uniform.
GammaPower	x	Incoming message from x.
Double	y	Constant value for y.
GammaPower	result	Modified to contain the outgoing message.

Returns

Type	Description
GammaPower	result

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_(pow) p(pow) factor(pow,x,y)]/p(x).

Exceptions

Type	Condition
ImproperMessageException	pow is not a proper distribution.

XAverageConditional(GammaPower, TruncatedGamma, Double)

EP message to x.

Declaration

public static TruncatedGamma XAverageConditional(GammaPower pow, TruncatedGamma x, double y)

Parameters

Type	Name	Description
GammaPower	pow	Incoming message from pow. Must be a proper distribution. If uniform, the result will be uniform.
TruncatedGamma	x	Incoming message from x.
Double	y	Constant value for y.

Returns

Type	Description
TruncatedGamma	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_(pow) p(pow) factor(pow,x,y)]/p(x).

Exceptions

Type	Condition
ImproperMessageException	pow is not a proper distribution.

XAverageConditional(GammaPower, Double)

EP message to x.

Declaration

public static Gamma XAverageConditional(GammaPower pow, double y)

Parameters

Type	Name	Description
GammaPower	pow	Incoming message from pow. Must be a proper distribution. If uniform, the result will be uniform.
Double	y	Constant value for y.

Returns

Type	Description
Gamma	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_(pow) p(pow) factor(pow,x,y)]/p(x).

Exceptions

Type	Condition
ImproperMessageException	pow is not a proper distribution.

XAverageConditional(Pareto, Gamma, Double)

EP message to x.

Declaration

public static Gamma XAverageConditional(Pareto pow, Gamma x, double y)

Parameters

Type	Name	Description
Pareto	pow	Incoming message from pow.
Gamma	x	Incoming message from x.
Double	y	Constant value for y.

Returns

Type	Description
Gamma	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_(pow) p(pow) factor(pow,x,y)]/p(x).

XAverageLogarithm(GammaPower, GammaPower, Double, GammaPower)

VMP message to x.

Declaration

public static GammaPower XAverageLogarithm(GammaPower pow, GammaPower x, double y, GammaPower result)

Parameters

Type	Name	Description
GammaPower	pow	Incoming message from pow. Must be a proper distribution. If uniform, the result will be uniform.
GammaPower	x	Incoming message from x.
Double	y	Constant value for y.
GammaPower	result	Modified to contain the outgoing message.

Returns

Type	Description
GammaPower	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	pow is not a proper distribution.

XAverageLogarithm(GammaPower, Double)

VMP message to x.

Declaration

public static Gamma XAverageLogarithm(GammaPower pow, double y)

Parameters

Type	Name	Description
GammaPower	pow	Incoming message from pow. Must be a proper distribution. If uniform, the result will be uniform.
Double	y	Constant value for y.

Returns

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

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	pow is not a proper distribution.