Module Interfaces.Sigs.Deriv.Deriv.Model

module Model: sig .. end

(Untrained) model with derivative information

type t

Type of models with derivatives

type hyper_t

Type of models for general hyper parameters

val calc : Interfaces.Sigs.Deriv.Deriv.Inputs.t ->
       sigma2:float -> t

calc inputs ~sigma2
Returns model with derivative information given inputs and noise level sigma2.

val update_sigma2 : t ->
       float -> t

update_sigma2 model sigma2
Returns model with derivative information by updating model with new noise level sigma2.

val calc_eval : t -> Interfaces.Sigs.Eval.Model.t

calc_eval model
Returns model without derivative information given model.

val calc_log_evidence_sigma2 : t -> float

calc_log_evidence_sigma2 model
Returns the derivative of the log evidence of model with respect to the noise level (sigma2).

val prepare_hyper : t ->
       hyper_t

prepare_hyper model
Returns the model prepared for calculating derivatives for arbitrary hyper parameters.

val calc_log_evidence : hyper_t ->
       Interfaces.Sigs.Deriv.Deriv.Spec.Hyper.t -> float

calc_log_evidence hyper_t hyper
Returns the derivative of the log evidence given prepared model hyper_t with respect to the hyper variable.