QoIEstimator

class axtreme.qoi.qoi_estimator.QoIEstimator(*args, **kwargs)

Bases: Protocol

A protocol for quantity of interest (QoI) estimators.

__init__(*args, **kwargs)

Methods

__init__(*args, **kwargs)
mean(x)	Function that computes the mean of the QoI estimates (the output of the call() method).
var(x)	Function that computes the variance of the QoI estimates (the output of the call() method).

mean(x: Tensor) → Tensor

Function that computes the mean of the QoI estimates (the output of the call() method).

For many applications this should just be using a default implementation that computes the mean. E.g using torch.mean(x).

However, in some special cases, it might be useful to provide a custom implementation to give a more accurate estimate. E.g. when UTSampler is used.

Parameters:

x – A tensor of QoI estimates with shape (number_of_estimates,).

Returns:

The mean of the QoI estimates. Should be a scalar.

Return type:

torch.Tensor

var(x: Tensor) → Tensor

Function that computes the variance of the QoI estimates (the output of the call() method).

For many applications this should just be using a default implementation that computes the variance. E.g. using torch.var(x).

However, in some special cases, it might be useful to provide a custom implementation to give a more accurate estimate. E.g. when UTSampler is used.

Parameters:

x – A tensor of QoI estimates with shape (number_of_estimates,).

Returns:

The variance of the QoI estimates. Should be a scalar.

Return type:

torch.Tensor