Class VariablePointOp_RpropBeta
Inherited Members
Namespace: Microsoft.ML.Probabilistic.Factors
Assembly: Microsoft.ML.Probabilistic.dll
Syntax
[FactorMethod(typeof(Clone), "VariablePoint<>", new Type[]{}, Default = true)]
[Buffers(new string[]{"bufferBeta"})]
[Quality(QualityBand.Preview)]
public class VariablePointOp_RpropBeta : VariablePointOpBase
Methods
BufferBeta(Beta, Beta, Beta, RpropBufferData)
Declaration
[SkipIfAllUniform]
public static RpropBufferData BufferBeta(Beta use, Beta def, Beta to_marginal, RpropBufferData bufferBeta)
Parameters
Type | Name | Description |
---|---|---|
Beta | use | |
Beta | def | |
Beta | to_marginal | |
RpropBufferData | bufferBeta |
Returns
Type | Description |
---|---|
RpropBufferData |
BufferBetaInit()
Declaration
public static RpropBufferData BufferBetaInit()
Returns
Type | Description |
---|---|
RpropBufferData |
MarginalAverageConditional(Beta, Beta, RpropBufferData, Beta)
EP message to marginal
.
Declaration
public static Beta MarginalAverageConditional(Beta use, Beta def, RpropBufferData bufferBeta, Beta result)
Parameters
Type | Name | Description |
---|---|---|
Beta | use | Incoming message from |
Beta | def | Incoming message from |
RpropBufferData | bufferBeta | Buffer |
Beta | result | Modified to contain the outgoing message. |
Returns
Type | Description |
---|---|
Beta |
|
Remarks
The outgoing message is a distribution matching the moments of marginal
as the random arguments are varied. The formula is proj[p(marginal) sum_(use,def) p(use,def) factor(use,def,marginal)]/p(marginal)
.