ibm_as_taylor: Compute a mapper linearisation

In inlabru: Bayesian Latent Gaussian Modelling using INLA and Extensions

Compute a mapper linearisation

Description

Implementations must return a bm_taylor object The linearisation information includes offset, jacobian, and state0. The state information indicates for which state the offset was evaluated, with NULL meaning all-zero. The linearised mapper output is defined as

effect(input, state) =
  offset(input, state0) + jacobian(input, state0) %*% (state - state0)

The default method calls ibm_eval2() to generate the needed information.

Usage

ibm_as_taylor(mapper, input, state = NULL, ...)

## Default S3 method:
ibm_as_taylor(mapper, input, state, ...)

## S3 method for class 'bm_multi'
ibm_as_taylor(mapper, input, state, inla_f = FALSE, ...)

## S3 method for class 'bm_collect'
ibm_as_taylor(mapper, input, state, inla_f = FALSE, ...)

## S3 method for class 'bm_expr'
ibm_as_taylor(
  mapper,
  input,
  state,
  ...,
  derived = NULL,
  jacobians = NULL,
  data = data,
  inla_f = FALSE
)

## S3 method for class 'bru_obs'
ibm_as_taylor(mapper, input, state, ..., multi = FALSE, comp_mappers)

## S3 method for class 'bru_obs_list'
ibm_as_taylor(
  mapper,
  input,
  state,
  ...,
  multi = FALSE,
  comp_mappers,
  eval_fun = NULL
)

## S3 method for class 'bm_repeat'
ibm_as_taylor(mapper, input, state, ...)

## S3 method for class 'bm_sum'
ibm_as_taylor(mapper, input, state, ...)

## S3 method for class 'bru_comp'
ibm_as_taylor(mapper, input, state = NULL, ...)

Arguments

mapper	A mapper S3 object, inheriting from bru_mapper.
input	Data input for the mapper.
state	A vector of latent state values for the mapping, of length ibm_n(mapper, inla_f = FALSE)
...	Arguments passed on to other methods
inla_f	logical; when TRUE for ibm_n() and ibm_values(), the result must be compatible with the INLA::f(...) and corresponding INLA::inla.stack(...) constructions. For ⁠ibm_{eval,jacobian,linear}⁠, the input interpretation may be different. Implementations do not normally need to do anything different, except for mappers of the type needed for hidden multicomponent models such as "bym2", which can be handled by bm_collect.
derived	The state vectors of variables derived from the root variables. If NULL or missing, defaults to an empty list.
jacobians	The state vectors of variables derived from the root If jacobians is NULL or missing, defaults to an empty list. If not NULL, should be a list with named entries, one for variable derived from the root variables. Each list element should be a named list of Jacobian matrices, with names matching the root variables. Missing entries are treated as all-zero matrices.
data	should be a list with data objects, with the main object called data; see bm_expr() for details.
multi	logical; If TRUE (or positive), recurse one level into sub-mappers
comp_mappers	A list of mappers, typically from ⁠as_bm_list<bru_comp_list>⁠.
eval_fun	A list of functions, typically from bru_eval_fun().

Value

A bm_taylor object. The state0 information in the affine mapper indicates for which state the offset was evaluated; The affine mapper output is defined as

effect(input, state) =
  offset(input, state0) + jacobian(input, state0) %*% (state - state0)

Methods (by class)

• ibm_as_taylor(default): Calls ibm_eval2() and returns a bm_taylor object.

See Also

Other mapper methods: bru_mapper_generics, ibm_eval(), ibm_eval2(), ibm_inla_subset(), ibm_invalid_output(), ibm_is_linear(), ibm_is_rowwise(), ibm_jacobian(), ibm_n(), ibm_n_output(), ibm_names(), ibm_simplify(), ibm_values()

Examples

m <- bm_linear()
ibm_as_taylor(m, input = c(1, 3, 4, 5, 2), state = 2)

inlabru documentation built on July 28, 2026, 9:07 a.m.