jade

JADE — Adaptive Differential Evolution with optional external archive

jade implements JADE: adaptive DE with the current-to-pbest mutation strategy. F and CR are adapted each generation using Cauchy and Normal distributions centered on success histories. An optional external archive stores recently replaced solutions to widen diversity in mutation.

Usage

jade(
  NP = 40,
  G = 100,
  data,
  class.name,
  c = 0.1,
  structure = c("nb", "tancl", "tan", "hc"),
  pB = 0.05,
  edgelist = NULL,
  archive = TRUE,
  verbose = 25,
  ...
)

Parameters

NP · integer · default: "40"

Population size. Must be > 5.

G · integer · default: "100"

Maximum generations.

data · data.frame · required

Data frame containing features and class variable.

class.name · character · required

Name of the class variable column.

c · numeric · default: "0.1"

Adaptation rate for updating mean F and CR. Must be in [0, 0.2].

structure · character · default: "nb"

BN structure: "nb", "tan", "tancl", or "hc".

pB · numeric · default: "0.05"

Fraction of population used as p-best pool for mutation. Must be in (0, 1].

edgelist · matrix

Optional custom BN topology (edges × 2 matrix: from, to).

archive · logical · default: "TRUE"

If TRUE, replaced individuals are stored in an external archive used in mutation.

verbose · integer · default: "25"

Print progress every this many generations.

...

Extra arguments passed to bnclassify::tan_cl or bnclassify::tan_hc.

Return value

Object of class DE with fields: Best, BestCLL, pobFinal, CLLPobFinal, N.evals, convergence, evaluations.

Example

library(dplbnDE)
data(car)

result <- jade(
  NP = 20, G = 25,
  data = car,
  class.name = names(car)[7],
  c = 0.1, pB = 0.05,
  structure = "hc",
  archive = TRUE,
  verbose = 5,
  k = 3
)
print(result)