Package dev.nm.stat.random.rng.multivariate.mcmc.hybrid

Class ErgodicHybridMCMC

java.lang.Object

dev.nm.stat.random.rng.multivariate.mcmc.hybrid.ErgodicHybridMCMC

All Implemented Interfaces:

RandomVectorGenerator, Seedable

public class ErgodicHybridMCMC
extends Object
implements RandomVectorGenerator

A simple decorator which will randomly vary dt between each sample. At each step dt is uniformly chosen from a given range. This avoids the possibility that the chosen dt produces a trajectory that is periodic for L leapfrog steps, and hence returns to (or close to) the starting point at each iteration. In cases where there are a lot of interactions between the components, this should not be an issue, although even near periodicities can have a significant adverse effect on the performance of the algorithm.

Constructor Summary

Constructors

Constructor	Description
ErgodicHybridMCMC(double a, double b, RandomLongGenerator uniform, AbstractHybridMCMC hybridMCMC)	Constructs a new instance where dt is uniformly drawn from a given range.
ErgodicHybridMCMC(double dt0, UnivariateRealFunction deltaT, AbstractHybridMCMC hybridMCMC)	Constructs a new instance where dt is given as a function.

Method Summary

Modifier and Type	Method	Description
double[]	nextVector()	Gets the next random vector.
void	seed(long... seeds)	Seed the random number/vector/scenario generator to produce repeatable experiments.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ErgodicHybridMCMC

public ErgodicHybridMCMC(double dt0,
 UnivariateRealFunction deltaT,
 AbstractHybridMCMC hybridMCMC)

Constructs a new instance where dt is given as a function.

Parameters:

dt0 - the initial value for dt

deltaT - the function that gives the next value of dt given the current value

hybridMCMC - the underlying AbstractHybridMCMC

ErgodicHybridMCMC

public ErgodicHybridMCMC(double a,
 double b,
 RandomLongGenerator uniform,
 AbstractHybridMCMC hybridMCMC)

Constructs a new instance where dt is uniformly drawn from a given range.

Parameters:

a - the lower bound of the range

b - the upper bound of the range

uniform - the random long generator to be used

hybridMCMC - the underlying AbstractHybridMCMC

Method Details

nextVector

public double[] nextVector()

Description copied from interface: RandomVectorGenerator

Gets the next random vector.

Specified by:

nextVector in interface RandomVectorGenerator

Returns:

the next random vector

seed

public void seed(long... seeds)

Description copied from interface: Seedable

Seed the random number/vector/scenario generator to produce repeatable experiments.

Specified by:

seed in interface Seedable

Parameters:

seeds - the seeds