Negated

class pmrf.evaluators.Negated(evaluator: AbstractEvaluator, *, name: str | None = None, metadata: Any = None)

Bases: AbstractEvaluator

Computes the negative of another evaluator.

This is a general sign flip: it reads nothing from the wrapped evaluator beyond calling it, so it works for any pmrf.evaluators.AbstractEvaluator.

Its most common use is turning a log-likelihood into a quantity to minimize, for example wrapping pmrf.evaluators.MarginalLogLikelihood or pmrf.evaluators.GibbsMarginalLogLikelihood for Maximum Likelihood Estimation.

Parameters:

evaluator (pmrf.evaluators.AbstractEvaluator) – The underlying evaluator to negate.

__call__(model: PyTree, frequency: Frequency, **kwargs) → Array

Evaluate the model response over the specified frequency range.

Parameters:

• model (PyTree) – The parameter PyTree to evaluate.

• freq (Frequency) – The frequency object defining the evaluation points.

• **kwargs (dict) – Additional keyword arguments for the evaluation process.

Returns:

The evaluated model response.

Return type:

jnp.ndarray

evaluator: AbstractEvaluator

The underlying evaluator instance.