pymc.smc.kernels.IMH

class pymc.smc.kernels.IMH(*args, correlation_threshold=0.01, **kwargs)

Independent Metropolis-Hastings SMC_kernel.

Methods

IMH.__init__(*args[, correlation_threshold])	Create the Independent Metropolis-Hastings SMC kernel object.
IMH.initialize(start, rng)	Initialize the kernel for sampling.
IMH.initialize_population()	Create an initial population from the prior distribution.
IMH.mutate()	Independent Metropolis-Hastings perturbation.
IMH.resample()	Resample particles based on importance weights.
IMH.sample_settings()	SMC_kernel settings to be saved once at the end of sampling.
IMH.sample_stats()	Stats to be saved at the end of each stage.
IMH.set_rng(rng)	Copy compiled functions, updating their random number generators.
IMH.setup_kernel()	Perform setup logic once before sampling starts.
IMH.step()	Perform a single SMC stage: resample, tune, and mutate.
IMH.tune()	Tuning logic performed before every mutation step.
IMH.update_beta_and_weights()	Calculate the next inverse temperature (beta).

Attributes

stats_dtypes_shapes