mcmc {BayesFluxR}

Sample from a BNN using MCMC

Description

Sample from a BNN using MCMC

Usage

mcmc(
  bnn,
  batchsize,
  numsamples,
  sampler = sampler.SGLD(stepsize_a = 1),
  continue_sampling = FALSE,
  start_value = NULL
)

Arguments

bnn

A BNN obtained using BNN

batchsize

batchsize to use; Most samplers allow for batching. For some, theoretical justifications are missing (HMC)

numsamples

Number of mcmc samples

sampler

Sampler to use; See for example sampler.SGLD and all other samplers start with 'sampler.' and are thus easy to identity.

continue_sampling

Do not start new sampling, but rather continue sampling For this, numsamples must be greater than the already sampled number.

start_value

Values to start from. By default these will be sampled using the initialiser in 'bnn'.

Value

a list containing the 'samples' and the 'sampler' used.

Examples

## Not run: 
  ## Needs previous call to `BayesFluxR_setup` which is time
  ## consuming and requires Julia and BayesFlux.jl
  BayesFluxR_setup(installJulia=TRUE, seed=123)
  net <- Chain(Dense(5, 1))
  like <- likelihood.feedforward_normal(net, Gamma(2.0, 0.5))
  prior <- prior.gaussian(net, 0.5)
  init <- initialise.allsame(Normal(0, 0.5), like, prior)
  x <- matrix(rnorm(5*100), nrow = 5)
  y <- rnorm(100)
  bnn <- BNN(x, y, like, prior, init)
  sampler <- sampler.SGNHTS(1e-3)
  ch <- mcmc(bnn, 10, 1000, sampler)

## End(Not run)