A kernel-density-based, embarrassingly parallel ensemble sampler

kombine is an ensemble sampler that uses a clustered kernel-density-estimate proposal density, allowing for massive parallelization and efficient sampling.

Example usage:

• 2-D Gaussian
• 2-D Rosenbrock

@article{kombine,
   author = {{Farr}, B. and {Farr}, W.~M.},
    title = {kombine: a kernel-density-based, embarrassingly parallel ensemble sampler},
     year = 2015,
     note = "in prep"
}

Copyright 2014 Ben Farr and contributors.

kombine is free software made available under the MIT License. For details see the LICENSE file.