# WeightedPredictiveVariance¶

The predictive variance acquisition function that yields uncertainty sampling.

The acquisition function is

$a(x) = \operatorname{Var}(f(x)) p(x)^2$

where $$\operatorname{Var}(f(x))$$ is the predictive variance of the model and $$p(x)$$ is the density of the integration measure $$\mu$$.

Attributes Summary

 has_gradients Whether the acquisition function exposes gradients.

Methods Summary

 __call__(x, bq_state) Evaluates the acquisition function and optionally its gradients.

Attributes Documentation

Methods Documentation

__call__(x, bq_state)[source]

Evaluates the acquisition function and optionally its gradients.

Parameters
• x (ndarray) – shape=(batch_size, input_dim) – The nodes where the acquisition function is being evaluated.

• bq_state (BQState) – State of the BQ belief.

Returns

• acquisition_valuesshape=(batch_size, ) – The acquisition values at nodes x.