Index

_

__call__() (AbstractAcquisition method), [1], [2] (AcquisitionFactory method) (ConditionalPredictive method) (ConditionalPredictiveFactory method) (ExpectedImprovementAcquisition method) (ExpectedImprovementAcquisitionFactory method), [1], [2] (GaussianProcessConditionalPredictive method) (GaussianProcessConditionalPredictiveFactory method), [1], [2] (MarginalisedAcquisitionFunction method), [1], [2] (MarginalisedConditionalPredictive method) (ScaledExpectedImprovementAcquisition method) (ScaledExpectedImprovementAcquisitionFactory method) (ScaledTopTwoAcquisition method) (ScaledTopTwoAcquisitionFactory method) (TopTwoAcquisition method) (TopTwoAcquisitionFactory method), [1], [2]

__hash__() (HashableSerialisableBaseModel method) __reduce__() (SerialisableBaseModel method)

A

AbstractAcquisition (class in bojaxns) (class in bojaxns.base) (class in bojaxns.gaussian_process_formulation)

AcquisitionFactory (class in bojaxns.base) add_trial_from_data() (BayesianOptimisation method), [1] apply_validators() (in module bojaxns.basic) arbitrary_types_allowed (SerialisableBaseModel.Config attribute)

B

BayesianOptimisation (class in bojaxns) (class in bojaxns.service) BayesianOptimiser (class in bojaxns) (class in bojaxns.gaussian_process_formulation) (class in bojaxns.gaussian_process_formulation.bayesian_optimiser) bojaxns module bojaxns.base module bojaxns.basic module bojaxns.common module bojaxns.experiment module bojaxns.gaussian_process_formulation module bojaxns.gaussian_process_formulation.bayesian_optimiser module

bojaxns.gaussian_process_formulation.distribution_math module bojaxns.gaussian_process_formulation.multi_step_lookahead module bojaxns.parameter_space module bojaxns.service module bojaxns.utils module build_example() (in module bojaxns) (in module bojaxns.basic) (in module bojaxns.utils) build_prior_model() (ConditionalPredictiveFactory method) (GaussianProcessConditionalPredictiveFactory method), [1], [2] (in module bojaxns) (in module bojaxns.parameter_space)

C

CategoricalPrior (class in bojaxns) (class in bojaxns.parameter_space) choose_next_U_multistep() (BayesianOptimiser method), [1], [2] choose_next_U_toptwo() (BayesianOptimiser method), [1], [2] ConditionalPredictive (class in bojaxns.base) ConditionalPredictiveFactory (class in bojaxns.base) ContinuousPrior (class in bojaxns) (class in bojaxns.parameter_space)

convert_tree_to_graph() (in module bojaxns) (in module bojaxns.gaussian_process_formulation) (in module bojaxns.gaussian_process_formulation.multi_step_lookahead) create_dt (Trial attribute), [1] create_new_experiment() (BayesianOptimisation class method), [1] create_new_trial() (BayesianOptimisation method), [1] current_utc() (in module bojaxns) (in module bojaxns.utils)

D

data (MultiLookAheadState attribute)

delete_trial() (BayesianOptimisation method), [1] depth (MultiLookAheadState attribute)

E

ensure_parameters_match_space() (OptimisationExperiment method), [1], [2], [3] example_from_schema() (in module bojaxns.basic) ExpectedImprovementAcquisition (class in bojaxns.gaussian_process_formulation.distribution_math) ExpectedImprovementAcquisitionFactory (class in bojaxns) (class in bojaxns.gaussian_process_formulation) (class in bojaxns.gaussian_process_formulation.distribution_math)

experiment (BayesianOptimisation property), [1] experiment_id (OptimisationExperiment attribute), [1], [2], [3]

F

FloatValue (class in bojaxns.common)

G

GaussianProcessConditionalPredictive (class in bojaxns.gaussian_process_formulation.distribution_math) GaussianProcessConditionalPredictiveFactory (class in bojaxns) (class in bojaxns.gaussian_process_formulation) (class in bojaxns.gaussian_process_formulation.distribution_math)

GaussianProcessData (class in bojaxns) (class in bojaxns.gaussian_process_formulation) (class in bojaxns.gaussian_process_formulation.distribution_math) get_trial() (BayesianOptimisation method), [1]

H

HashableSerialisableBaseModel (class in bojaxns.basic)

I

init_explore_size (NewExperimentRequest attribute), [1] IntegerPrior (class in bojaxns) (class in bojaxns.parameter_space)

IntValue (class in bojaxns.common) InvalidTrial, [1]

J

json_encoders (SerialisableBaseModel.Config attribute)

L

latin_hypercube() (in module bojaxns) (in module bojaxns.utils) log_dp_mean (MarginalisationData attribute), [1], [2]

log_normal() (in module bojaxns.gaussian_process_formulation.distribution_math) log_normal_with_mask() (in module bojaxns.gaussian_process_formulation.distribution_math) lower (ContinuousPrior attribute), [1] (IntegerPrior attribute), [1]

M

marginal_likelihood() (ConditionalPredictive method) (GaussianProcessConditionalPredictive method) (MarginalisedConditionalPredictive method) MarginalisationData (class in bojaxns) (class in bojaxns.base) (class in bojaxns.gaussian_process_formulation) MarginalisedAcquisitionFunction (class in bojaxns) (class in bojaxns.base) (class in bojaxns.gaussian_process_formulation) MarginalisedConditionalPredictive (class in bojaxns.base) measurement_dt (TrialUpdate attribute), [1] mode (ContinuousPrior attribute), [1] (IntegerPrior attribute), [1]

module bojaxns bojaxns.base bojaxns.basic bojaxns.common bojaxns.experiment bojaxns.gaussian_process_formulation bojaxns.gaussian_process_formulation.bayesian_optimiser bojaxns.gaussian_process_formulation.distribution_math bojaxns.gaussian_process_formulation.multi_step_lookahead bojaxns.parameter_space bojaxns.service bojaxns.utils MultiLookAheadState (class in bojaxns.gaussian_process_formulation.multi_step_lookahead)

N

name (Parameter attribute), [1] ndims (ConditionalPredictive property) ndims() (ConditionalPredictiveFactory method) (GaussianProcessConditionalPredictiveFactory method), [1], [2]

NewExperimentRequest (class in bojaxns) (class in bojaxns.experiment) NotEnoughData

O

objective_measurement (TrialUpdate attribute), [1] OptimisationExperiment (class in bojaxns), [1] (class in bojaxns.experiment) (class in bojaxns.gaussian_process_formulation)

P

param_values (Trial attribute), [1] Parameter (class in bojaxns) (class in bojaxns.parameter_space) parameter_space (NewExperimentRequest attribute), [1] (OptimisationExperiment attribute), [1], [2], [3] parameters (ParameterSpace attribute), [1] ParameterSpace (class in bojaxns) (class in bojaxns.parameter_space)

ParamValues (in module bojaxns.common) post_measurement() (BayesianOptimisation method), [1] posterior() (ConditionalPredictive method) (GaussianProcessConditionalPredictive method) (MarginalisedConditionalPredictive method) posterior_solve() (BayesianOptimiser method), [1], [2] prior (Parameter attribute), [1] probs (CategoricalPrior attribute), [1] psd_kernels() (GaussianProcessConditionalPredictiveFactory method), [1], [2]

R

ref_id (TrialUpdate attribute), [1] RewardFnType (in module bojaxns.gaussian_process_formulation.multi_step_lookahead)

run_multi_lookahead() (in module bojaxns) (in module bojaxns.gaussian_process_formulation) (in module bojaxns.gaussian_process_formulation.multi_step_lookahead)

S

sample_size (GaussianProcessData attribute), [1], [2] samples (MarginalisationData attribute), [1], [2] ScaledExpectedImprovementAcquisition (class in bojaxns.gaussian_process_formulation.distribution_math) ScaledExpectedImprovementAcquisitionFactory (class in bojaxns.gaussian_process_formulation.distribution_math) ScaledTopTwoAcquisition (class in bojaxns.gaussian_process_formulation.distribution_math)

ScaledTopTwoAcquisitionFactory (class in bojaxns.gaussian_process_formulation.distribution_math) search_U_top1() (BayesianOptimiser method), [1], [2] search_U_top2() (BayesianOptimiser method), [1], [2] SerialisableBaseModel (class in bojaxns.basic) SerialisableBaseModel.Config (class in bojaxns.basic) static_fori_loop() (in module bojaxns.gaussian_process_formulation.multi_step_lookahead)

T

tfpb (in module bojaxns) (in module bojaxns.gaussian_process_formulation) (in module bojaxns.gaussian_process_formulation.bayesian_optimiser) tfpd (in module bojaxns.gaussian_process_formulation.distribution_math) TopTwoAcquisition (class in bojaxns.gaussian_process_formulation.distribution_math) TopTwoAcquisitionFactory (class in bojaxns) (class in bojaxns.gaussian_process_formulation) (class in bojaxns.gaussian_process_formulation.distribution_math) Trial (class in bojaxns) (class in bojaxns.experiment)

trial_id (Trial attribute), [1] trial_size() (BayesianOptimisation method), [1] trial_updates (Trial attribute), [1] trials (OptimisationExperiment attribute), [1], [2], [3] TrialUpdate (class in bojaxns) (class in bojaxns.experiment) type (CategoricalPrior attribute), [1] (ContinuousPrior attribute), [1] (FloatValue attribute) (IntegerPrior attribute), [1] (IntValue attribute)

U

U (GaussianProcessData attribute), [1], [2] U_value (Trial attribute), [1] uncert (ContinuousPrior attribute), [1] (IntegerPrior attribute), [1]

unique_parameters() (ParameterSpace method), [1] upper (ContinuousPrior attribute), [1] (IntegerPrior attribute), [1] UValue (in module bojaxns.common)

V

validate_assignment (SerialisableBaseModel.Config attribute) value (FloatValue attribute) (IntValue attribute)

visualise() (BayesianOptimisation method), [1]

Y

Y (GaussianProcessData attribute), [1], [2]

Y_var (GaussianProcessData attribute), [1], [2]