bilby.core.sampler.dynesty_utils.propose_volumetric

bilby.core.sampler.dynesty_utils.propose_volumetric(u, axes, scale, n, n_cluster, rstate)

Propose a new point using the default dynesty proposal.

The new difference vector is scaled by a vector isotropically drawn from an ellipsoid centered on zero with covariance given by the provided axis. Note that the magnitude of this proposal is heavily skewed to the size of the ellipsoid.

Parameters:

u: np.ndarray

The current point.

n: int

The number of dimensions being explored.

scale: float

The amount to scale the proposed point by.

n_cluster: int

The number of dimensions to run the differential evolution over, the first n_cluster dimensions are used. The rest are randomly sampled from the prior.

rstate: np.random.RandomState

The random state to use to generate random numbers.

Returns:

u_prop: np.ndarray

The proposed point.