base

bojaxns.base

Module Contents

class AbstractAcquisition[source]

A class that represents any acquisition function. All acquisition functions take a point in the U-domain and returns a metric that gives a proxy as to how valuable it would be to try that point. All acquisition values only make sense relatively.

abstract __call__(u_star)[source]
Parameters:

u_star (jax.numpy.ndarray) –

class ConditionalPredictive[source]
property ndims[source]
abstract posterior()[source]
abstract marginal_likelihood()[source]
abstract __call__(U_star, cov=False)[source]
Parameters:

  • U_star (jax.numpy.ndarray) –

  • cov (bool) –

class MarginalisationData[source]

Bases: NamedTuple

samples: Dict[str, chex.Array][source]
log_dp_mean: chex.Array[source]
class ConditionalPredictiveFactory[source]
abstract ndims()[source]
abstract build_prior_model()[source]
Return type:

jaxns.PriorModelType

abstract __call__(**samples)[source]
Return type:

ConditionalPredictive

class AcquisitionFactory[source]
abstract __call__(**sample)[source]
Return type:

AbstractAcquisition

class MarginalisedAcquisitionFunction(key, ns_results, acquisition_factory, S)[source]

Bases: AbstractAcquisition

Class that represents a marginalisation of an acquisition function over samples.

Parameters:
__call__(u_star)[source]
Parameters:

u_star (jax.numpy.ndarray) –

class MarginalisedConditionalPredictive(key, ns_results, conditional_predictive_factory, S)[source]

Bases: ConditionalPredictive

Class that represents a marginalisation of an acquisition function over samples.

Parameters:
posterior()[source]
marginal_likelihood()[source]
__call__(U_star, cov=False)[source]
Parameters:

  • U_star (jax.numpy.ndarray) –

  • cov (bool) –