pydpf.resampling.DiffusionResampler

class pydpf.resampling.DiffusionResampler(alpha, diffusion_time, n_steps, generator, schedule=None, jitter=0.0)

Bases: Module

Diffusion resampling [1].

Diffusion resampling constructs a backward diffusion from a reference distribution to the weighted posterior. The forward diffusion is represented by a Langevin SDE:

\[dX(s) = b^{2} \nabla \log \pi_{\text{ref}}(X(s)) \, ds + \sqrt{2}\, b \, dW(s)\]

\[X(0) \sim \sum_{i=1}^{N} w^{(i)}_{t} \, \delta_{x^{(i)}_{t}}\]

In this implementation we restrict the reference distribution \(\pi_{\text{ref}}\) to be Gaussian. Specifically, we fit a Gaussian distribution with independent dimensions to the weighted posterior. The backward diffusion’s drift and diffusion coefficients are then analytically available at any time \(s\).

Parameters:

alpha: float

The noising strength, determines the size of the forward diffusion coefficient, must be negative. More negative alpha corresponds to a faster forward diffusion.

diffusion_time: float

The maximum time of the forward diffusion. If a schedule is provided then i.e. schedule is not None then this parameter is ignored.

n_steps: int

The number of EM integrator steps to use in total. If a schedule is provided then i.e. schedule is not None then this parameter is ignored.

schedule: (S,) Tensor or None, Default: None

The discrete times at which the EM integrator is evaluated. If schedule is None then the integrator schedule is set to the n_steps + 1 uniformly spaced points in [0, diffusion_time].

jitter: float, Default: 0.

A tolerance parameter to ensure numerical stability if the covariance of the weighted posterior is very small. Must be non-negative.

Notes

Our implementation follows the code in the repository accompanying [1], and has a number of small differences to the pseudocode in their paper. In [1] various SDE solvers are experimented with and a deterministic ODE that approximates the SDE is tried. Currently, we only implement the Euler-Maruyama integrator for the SDE formulation.

References

[1] (1,2,3)

Andersson and Zhao, Diffusion differentiable resampling, 2025.

__init__(alpha, diffusion_time, n_steps, generator, schedule=None, jitter=0.0)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(alpha, diffusion_time, n_steps, ...)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
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()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(state, weight, **data)	Run the diffusion resampler.
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.
log_pdf(x, mu, sigma)
modules([remove_duplicate])	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
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_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before 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_post_hook(hook)	Register a post-hook for the state_dict() method.
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.
set_submodule(target, module[, strict])	Set the submodule given by target if it exists, otherwise throw an error.
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.
update()	Update all constrained_parameters and cached_properties belonging to this Module.
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
call_super_init
dump_patches
training

forward(state, weight, **data)

Run the diffusion resampler.

log_pdf(x, mu, sigma)