saealib.MeanPrediction#

class saealib.MeanPrediction(weights=None, reference=None, direction=None)[source]#

Bases: PointwiseAcquisition

Acquisition function based on predicted mean value (exploitation).

For single-objective problems, returns the predicted mean directly. For multi-objective problems, returns a weighted scalarization of the predicted mean.

A higher score indicates a more promising candidate. The sign convention follows the weight: use a negative weight for minimization (e.g., weights=np.array([-1.0])) so that lower objective values yield higher scores.

Parameters:

weights (np.ndarray or None) – Weights for magnitude-aware scalarization of multi-objective predictions. shape: (n_obj,). If None and direction is also None, uses the first objective only.
direction (np.ndarray or None) – Per-objective optimization directions (+1 = maximize, -1 = minimize). Used for direction-only scalarization when magnitude does not matter. Takes precedence over weights when both are provided. When unset, it is auto-injected from problem.direction at run start.
reference (Any)

Methods

`__init__`
`compute_reference`	Return fixed reference if set, otherwise None.
`contract`	Return the pointwise acquisition contract.
`evaluate`	Reject `prediction is None`, resolve the reference, then `score()`.
`prepare`	Delegate to `compute_reference(archive, rng=ctx.rng if ctx else None)`.
`score`	Compute scores based on predicted mean.

Method Details

MeanPrediction.__init__(weights=None, reference=None, direction=None)[source]#

Parameters:

weights (ndarray | None)
reference (Any)
direction (ndarray | None)

MeanPrediction.compute_reference(archive, rng=None)[source]#

Return fixed reference if set, otherwise None.

Parameters:

archive (Archive)
rng (np.random.Generator | None)

Return type:

Any

MeanPrediction.contract()#

Return the pointwise acquisition contract.

Return type:: ComponentContract

MeanPrediction.evaluate(candidates_x, prediction, archive, ctx=None, *, prepared=<object object>)#

Reject prediction is None, resolve the reference, then score().

See AcquisitionFunction.evaluate() for the shared parameter contract, including the _UNSET vs. explicit prepared=None distinction.

Parameters:

candidates_x (np.ndarray)
prediction (SurrogatePrediction | None)
archive (Archive)
ctx (OptimizationState | None)
prepared (Any)

Return type:

AcquisitionResult

MeanPrediction.prepare(archive, ctx=None)#

Delegate to compute_reference(archive, rng=ctx.rng if ctx else None).

Parameters:

archive (Archive)
ctx (OptimizationState | None)

Return type:

Any

MeanPrediction.score(prediction, reference=None, rng=None)[source]#

Compute scores based on predicted mean.

Parameters:

prediction (SurrogatePrediction) – Surrogate predictions. prediction.value shape: (n_samples, n_obj)
reference (Any) – Not used. Accepted for interface compatibility.
rng (Generator | None)

Returns:

Scores. shape: (n_samples,)

Return type:

np.ndarray