GitHub

Distribution sampling

ConsensusBasedX.jl also provides Consensus-Based Sampling.

The package exports sample, which behaves exactly as minimise in Function minimisation. It assumes you have defined a function f(x::AbstractVector) that takes a single vector argument x of length D = length(x).

For instance, if D = 2, you can sample exp(-αf) by running:

out = sample(f, D = 2, extended_output=true)
out.sample

The method must be run with the extended_output=true option in order to receive Extended output and access the full particle sample; without it, sample returns a single Vector{Float64} of length D which contains the candidate to the global minimiser of f, just like minimise.

Note

You must always provide D.

Full example
using ConsensusBasedX
f(x) = ConsensusBasedX.Ackley(x, shift = 1)
out = sample(f, D = 2, N = 20, extended_output = true)
out.sample

Using a config object

For more advanced usage, you will select several options. You can pass these as extra keyword arguments to sample, or you can create a NamedTuple called config and pass that:

config = (; D = 2, extended_output=true)
out = sample(f, config)
out.sample
Note

If you pass a Dict instead, it will be converted to a NamedTuple automatically.

Full example
using ConsensusBasedX
f(x) = ConsensusBasedX.Ackley(x, shift = 1)
config = (; D = 2, N = 20, extended_output = true)
out = sample(f, config)
out.sample

Running on minimisation mode

Consensus-based sampling can also be used for minimisation (see Consensus-Based Sampling). If you want to run it in that mode, pass the option CBS_mode = :minimise.

Method reference

ConsensusBasedX.sample — Function
sample(f; keywords...)
sample(f, config::NamedTuple)

Sample the distribution exp(-αf) using Consensus-Based Sampling (see Distribution sampling).

You must specify the dimension D of the problem. Other paramters (e.g. the number of particles N or the number of ensembles M) can also be specified; see Summary of options.

Examples

out = sample(f, D = 2, extended_output = true);
out.sample
config = (; D = 2, extended_output = true);
out = sample(f, config);
out.sample
out = sample(f, D = 2, N = 20, extended_output = true);
out.sample
config = (; D = 2, N = 20, extended_output = true);
out = sample(f, config);
out.sample
source