littlemcmc.step_sizes.DualAverageAdaptation

class littlemcmc.step_sizes.DualAverageAdaptation(initial_step, target, gamma, k, t0)

Dual averaging step size adaptation.

__init__(initial_step, target, gamma, k, t0)

Class for dual averaging step size adaptation.

Parameters:

initial_step

target

gamma : float, default .05

k : float, default .75

Parameter for dual averaging for step size adaptation. Values between 0.5 and 1 (exclusive) are admissible. Higher values correspond to slower adaptation.

t0 : int, default 10

Parameter for dual averaging. Higher values slow initial adaptation.

Methods

__init__(initial_step, target, gamma, k, t0)	Class for dual averaging step size adaptation.
current(tune)	Get current step size.
reset()	Reset step size adaptation routine.
stats()	Get step size adaptation statistics.
update(accept_stat, tune)	Update step size.
warnings()	Generate warnings from dual averaging step size adaptation.