Numeric.MCMC.Metropolis

This implementation uses spherical Gaussian proposals to implement a reliable and computationally inexpensive sampling routine. It can be used as a baseline from which to benchmark other algorithms for a given problem.

The mcmc function streams a trace to stdout to be processed elsewhere, while the metropolis transition can be used for more flexible purposes, such as working with samples in memory.

Documentation

mcmc :: (Traversable f, Show (f Double)) => Int -> Double -> f Double -> (f Double -> Double) -> Gen RealWorld -> IO ()

Trace n iterations of a Markov chain and stream them to stdout.

>>> let rosenbrock [x0, x1] = negate (5  *(x1 - x0 ^ 2) ^ 2 + 0.05 * (1 - x0) ^ 2)
>>> withSystemRandom . asGenIO $ mcmc 3 1 [0, 0] rosenbrock
0.5000462419822702,0.5693944056267897
0.5000462419822702,0.5693944056267897
-0.7525995304580824,1.2240725505283248

metropolis :: (Traversable f, PrimMonad m) => Double -> Transition m (Chain (f Double) b)

A generic Metropolis transition operator.

Re-exported

module Data.Sampling.Types

create :: PrimMonad m => m (Gen (PrimState m))

Create a generator for variates using a fixed seed.

createSystemRandom :: IO GenIO

Seed a PRNG with data from the system's fast source of pseudo-random numbers. All the caveats of withSystemRandom apply here as well.

withSystemRandom :: PrimBase m => (Gen (PrimState m) -> m a) -> IO a

Seed a PRNG with data from the system's fast source of pseudo-random numbers ("/dev/urandom" on Unix-like systems or RtlGenRandom on Windows), then run the given action.

This is a somewhat expensive function, and is intended to be called only occasionally (e.g. once per thread). You should use the Gen it creates to generate many random numbers.

asGenIO :: (GenIO -> IO a) -> GenIO -> IO a

Constrain the type of an action to run in the IO monad.