mcmc-samplers-0.1.1.1: Combinators for MCMC sampling

Safe HaskellNone
LanguageHaskell2010

MCMC.Kernels

Contents

Synopsis

Making the random walk

walk

Arguments

:: Step x

The stepping style (based on the transition kernel)

-> x

The starting state

-> Int

The number of steps to take

-> Rand

A PRNG

-> Action x IO a b

An action to take at each step in the walk

-> IO b

The action-dependent output at the end of the walk

Execute a random walk and create a Markov chain.

Transition kernels

Metropolis-Hastings

Simulated Annealing

type Temp = Double

type CoolingSchedule = Temp -> Temp

This is the tempering function used in the simulated annealing process.

Gibbs

gibbs :: Target a -> [a -> Proposal a] -> Step a

The full conditional proposals must be specified to this transition kernel.