Class DiscreteUniform

Provides outgoing messages for DiscreteUniform(Int32), given random arguments to the function.

Inheritance

Object

DiscreteUniform

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), "DiscreteUniform", new Type[]{})]
[Quality(QualityBand.Mature)]
public static class DiscreteUniform

Remarks

Factor is f(sample, size) = 1(sample < size)/size

Methods

AverageLogFactor(Discrete, Discrete)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Discrete sample, Discrete size)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample.
Discrete	size	Incoming message from size.

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,size) p(sample,size) log(factor(sample,size)). Adding up these values across all factors and variables gives the log-evidence estimate for VMP.

AverageLogFactor(Discrete, Int32)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(Discrete sample, int size)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample.
Int32	size	Constant value for size.

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

AverageLogFactor(Int32, Discrete)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(int sample, Discrete size)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Discrete	size	Incoming message from size.

Returns

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

Remarks

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

AverageLogFactor(Int32, Int32)

Evidence message for VMP.

Declaration

public static double AverageLogFactor(int sample, int size)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Int32	size	Constant value for size.

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

LogAverageFactor(Discrete, Discrete)

Evidence message for EP.

Declaration

public static double LogAverageFactor(Discrete sample, Discrete to_sample)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample.
Discrete	to_sample	Outgoing message to sample.

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) p(sample) factor(sample,size)).

LogAverageFactor(Int32, Discrete)

Evidence message for EP.

Declaration

public static double LogAverageFactor(int sample, Discrete size)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Discrete	size	Incoming message from size.

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_(size) p(size) factor(sample,size)).

LogAverageFactor(Int32, Int32)

Evidence message for EP.

Declaration

public static double LogAverageFactor(int sample, int size)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Int32	size	Constant value for size.

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(sample,size)).

LogEvidenceRatio(Discrete, Discrete)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Discrete sample, Discrete size)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample. Must be a proper distribution. If uniform, the result will be uniform.
Discrete	size	Incoming message from size.

Returns

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

Remarks

The formula for the result is log(sum_(sample,size) p(sample,size) factor(sample,size) / 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.

LogEvidenceRatio(Discrete, Int32)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(Discrete sample, int size)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample. Must be a proper distribution. If uniform, the result will be uniform.
Int32	size	Constant value for size.

Returns

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

Remarks

The formula for the result is log(sum_(sample) p(sample) factor(sample,size) / 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.

LogEvidenceRatio(Int32, Discrete)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(int sample, Discrete size)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Discrete	size	Incoming message from size.

Returns

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

Remarks

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

LogEvidenceRatio(Int32, Int32)

Evidence message for EP.

Declaration

public static double LogEvidenceRatio(int sample, int size)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Int32	size	Constant value for size.

Returns

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

Remarks

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

SampleAverageConditional(Discrete, Discrete)

EP message to sample.

Declaration

public static Discrete SampleAverageConditional(Discrete size, Discrete result)

Parameters

Type	Name	Description
Discrete	size	Incoming message from size.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

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_(size) p(size) factor(sample,size)]/p(sample).

SampleAverageConditional(Int32, Discrete)

EP message to sample.

Declaration

public static Discrete SampleAverageConditional(int size, Discrete result)

Parameters

Type	Name	Description
Int32	size	Constant value for size.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

Remarks

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

SampleAverageConditionalInit(Discrete)

Declaration

public static Discrete SampleAverageConditionalInit(Discrete size)

Parameters

Type	Name	Description
Discrete	size	Incoming message from size.

Returns

Type	Description
Discrete

Remarks

SampleAverageConditionalInit(Int32)

Declaration

public static Discrete SampleAverageConditionalInit(int size)

Parameters

Type	Name	Description
Int32	size	Constant value for size.

Returns

Type	Description
Discrete

Remarks

SampleAverageLogarithm(Discrete, Discrete)

VMP message to sample.

Declaration

public static Discrete SampleAverageLogarithm(Discrete size, Discrete result)

Parameters

Type	Name	Description
Discrete	size	Incoming message from size.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

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_(size) p(size) log(factor(sample,size))).

SampleAverageLogarithm(Int32, Discrete)

VMP message to sample.

Declaration

public static Discrete SampleAverageLogarithm(int size, Discrete result)

Parameters

Type	Name	Description
Int32	size	Constant value for size.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

Remarks

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

SampleAverageLogarithmInit(Discrete)

Declaration

public static Discrete SampleAverageLogarithmInit(Discrete size)

Parameters

Type	Name	Description
Discrete	size	Incoming message from size.

Returns

Type	Description
Discrete

Remarks

SampleAverageLogarithmInit(Int32)

Declaration

public static Discrete SampleAverageLogarithmInit(int size)

Parameters

Type	Name	Description
Int32	size	Constant value for size.

Returns

Type	Description
Discrete

Remarks

SizeAverageConditional(Discrete, Discrete)

EP message to size.

Declaration

public static Discrete SizeAverageConditional(Discrete sample, Discrete result)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample. Must be a proper distribution. If uniform, the result will be uniform.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	sample is not a proper distribution.

SizeAverageConditional(Int32, Discrete)

EP message to size.

Declaration

public static Discrete SizeAverageConditional(int sample, Discrete result)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

Remarks

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

SizeAverageLogarithm(Discrete, Discrete)

VMP message to size.

Declaration

public static Discrete SizeAverageLogarithm(Discrete sample, Discrete result)

Parameters

Type	Name	Description
Discrete	sample	Incoming message from sample. Must be a proper distribution. If uniform, the result will be uniform.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

Remarks

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

Exceptions

Type	Condition
ImproperMessageException	sample is not a proper distribution.

SizeAverageLogarithm(Int32, Discrete)

VMP message to size.

Declaration

public static Discrete SizeAverageLogarithm(int sample, Discrete result)

Parameters

Type	Name	Description
Int32	sample	Constant value for sample.
Discrete	result	Modified to contain the outgoing message.

Returns

Type	Description
Discrete	result

Remarks

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