Mixin¶
-
class
pysgmcmc.samplers.mixin.SamplerMixin(negative_log_likelihood, params, *args, **kwargs)[source]¶ Mixin class that turns a torch.nn.optim.Optimizer into a MCMC sampler.
-
__init__(negative_log_likelihood, params, *args, **kwargs)[source]¶ - Instantiate a sampler object.
- (Initial) parameters are passed as iterable params, negative_log_likelihood is a function mapping parameters to a NLL value and *args and **kwargs allow specifying additional arguments to pass to a sampler, e.g. lr or mdecay.
Parameters: - negative_log_likelihood (typing.Callable[[typing.Iterable[torch.Tensor]], torch.Tensor]) – Callable mapping parameters to a NLL value.
- params (iterable) – Iterable of parameters used to construct samples.
See also
pysgmcmc.samplers.sghmc.SGHMC()- SGHMC sampler that uses this mixin.
-
__next__()[source]¶ - Perform a step of this sampler and return parameters with costs.
- Together with __iter__, this allows using samplers as iterables.
Returns: - parameters (typing.Tuple[numpy.ndarray, …]) – Current parameters.
- cost (torch.Tensor) – NLL value associated with parameters.
-
__weakref__¶ list of weak references to the object (if defined)
-
parameters¶ Return last sample as tuple of numpy arrays.
Returns: current_parameters – Tuple of numpy arrays containing last sampled values. Return type: typing.Tuple[numpy.ndarray, ..]
-