gw.inference.inference_utils.prepare_log_prob

gw.inference.inference_utils.prepare_log_prob(
    sampler,
    num_samples,
    nde_settings,
    batch_size=None,
    threshold_std=np.inf,
    remove_init_outliers=0.0,
    low_latency_label=None,
    outdir=None,
)

Prepare gnpe sampling with log_prob. This is required, since in its vanilla form gnpe does not provide the density for its samples.

Specifically, we train an unconditional neural density estimator (nde) for the gnpe proxies. This requires running the gnpe sampler till convergence, and extracting the gnpe proxies after the final gnpe iteration. The nde is trained to match the distribution over gnpe proxies, which provides a way of rapidly sampling (converged!) gnpe proxies and evaluating the log_prob.

After this preparation step, self.run_sampler can leverage self.gnpe_proxy_sampler (which is based on the aforementioned trained nde) to sample gnpe proxies, such that one gnpe iteration is sufficient. The log_prob of the samples in the joint space (inference parameters + gnpe proxies) is then simply given by the sum of the corresponding log_probs (from self.model and self.gnpe_proxy_sampler.model).

Parameters

Name	Type	Description	Default
num_samples	int	number of samples for training of nde	required
batch_size	Optional[int]	batch size for sampler	None
threshold_std	Optional[float]	gnpe proxies deviating by more then threshold_std standard deviations from the proxy mean (along any axis) are discarded.	np.inf
low_latency_label	str	File label for low latency samples (= samples used for training nde). If None, these samples are not saved.	None
outdir	str	Directory in which low latency samples are saved. Needs to be set if low_latency_label is not None.	None