UTSampler

class axtreme.sampling.ut_sampler.UTSampler(alpha: float = 1, beta: float = 2, kappa_base: float = 3)

Bases: IndependentMCSampler

Class for sampling a posterior using the Unscented Transform.

The Unscented Transform is a method for transforming a distribution through a non-linear function. The method is based on the Unscented Kalman Filter. It uses a set of sigma points to estimate the mean and covariance of the transformed distribution.

__init__(alpha: float = 1, beta: float = 2, kappa_base: float = 3) → None

Initializer for the UTSampler.

Parameters:

• alpha – Scaling parameter for the sigma points. See filterpy.kalman.MerweScaledSigmaPoints.

• beta – Parameter for the distribution. - For Gaussian distributions, beta=2 is optimal. - See filterpy.kalman.MerweScaledSigmaPoints.

• kappa_base – Base parameter for the sigma points. See filterpy.kalman.MerweScaledSigmaPoints.

Methods

__init__([alpha, beta, kappa_base])	Initializer for the UTSampler.
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Set the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(posterior)	Draw samples from the posterior, treating each of the n input points as independant.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
mean(transformed_points[, dim])	Estimate the mean of the transformed UT sampled points.
modules()	Return an iterator over all modules in the network.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post hook to be run after module's load_state_dict is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
var(transformed_points[, dim])	Estimate the variance of the transformed UT sampled points.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

Attributes

T_destination
alpha	The alpha parameter defined by filterpy.kalman.MerweScaledSigmaPoints.
beta	The beta parameter defined by filterpy.kalman.MerweScaledSigmaPoints.
call_super_init
dump_patches
kappa_base	The kappa_base parameter related to kappa defined by filterpy.kalman.MerweScaledSigmaPoints.
training

mean(transformed_points: Tensor, dim: int = 0) → Tensor

Estimate the mean of the transformed UT sampled points.

The UT sampled points are designed together with the weights to estimate the mean of the distribution When the points are transformed through some function, the mean of the transformed points is estimated by calculating the weighted sum of the points.

This will only work correctly if the last points generated using this sampler

• Have the same number of targets (m) the transformed points.

• Were generated using the same alpha, beta, and kappa_base parameters.

Parameters:

• transformed_points – The transformed points to estimate the mean of.

• dim – The dimension along which to calculate the mean.

Returns:

The estimated mean of the distribution.

var(transformed_points: Tensor, dim: int = 0) → Tensor

Estimate the variance of the transformed UT sampled points.

The UT sampled points are designed together with the weights to estimate the variance of the distribution When the points are transformed through some function, the variance of the transformed points is estimated by calculating the weighted sum of the points.

This will only work correctly if the last points generated using this sampler

• Have the same number of targets (m) as the transformed points.

• Were generated using the same alpha, beta, and kappa_base parameters.

Parameters:

• transformed_points – The transformed points to estimate the variance of.

• dim – The dimension along which to calculate the variance.

Returns:

The estimated variance of the distribution.

property alpha: float

The alpha parameter defined by filterpy.kalman.MerweScaledSigmaPoints.

property beta: float

The beta parameter defined by filterpy.kalman.MerweScaledSigmaPoints.

property kappa_base: float

The kappa_base parameter related to kappa defined by filterpy.kalman.MerweScaledSigmaPoints.

The kappa value used in filterpy.kalman.MerweScaledSigmaPoints is calculated as kappa_base - num_target.