None training : bool ¶ Monte-Carlo Acquisition Function API ¶ class _carlo. Objective ( Optional ) – A ScalarizedObjective (optional). Model ( Model) – A fitted single-outcome model. AnalyticAcquisitionFunction ( model, objective = None ) ¶īase class for analytic acquisition functions.īase constructor for analytic acquisition functions. Torch.Tensor training : bool ¶ Analytic Acquisition Function API ¶ class. X_full ( torch.Tensor) – A b x q_aug x d-dim Tensor with b t-batches of q_augĪ b x q x d-dim Tensor with b t-batches of q design points each.
#Expected objective function nonmem full#
Int abstract extract_candidates ( X_full ) ¶Įxtract the candidates from a full “one-shot” parameterization. The augmented size for one-shot optimization (including variables Q ( int) – The number of candidates to consider jointly. Get augmented q batch size for one-shot optimziation. None abstract get_augmented_q_batch_size ( q ) ¶ OneShotAcquisitionFunction ( model ) ¶īases:, abc.ABCĪbstract base class for acquisition functions using one-shot optimization X ( torch.Tensor) – A (b) x q x d-dim Tensor of (b) t-batches with q d-dimĪ (b)-dim Tensor of acquisition function values at the given Return typeĮvaluate the acquisition function on the candidate set X.
X_pending ( Optional ) – n x d Tensor with n d-dim design points that haveīeen submitted for evaluation but have not yet been evaluated. Informs the acquisition function about pending design points. None set_X_pending ( X_pending = None ) ¶ AcquisitionFunction ( model ) ¶īases: torch.nn., abc.ABCĪbstract base class for acquisition functions.Ĭonstructor for the AcquisitionFunction base class.
Botorch.acquisition ¶ Acquisition Function APIs ¶ Abstract Acquisition Function APIs ¶Ībstract base module for all botorch acquisition functions.
0 kommentar(er)
