Table 8 Theoretical time complexity of optimization methods (Big-O notation).

From: A hybrid CNN-transformer framework optimized by Grey Wolf Algorithm for accurate sign language recognition

Optimizer

Big-O complexity

Remarks

PSO

O(N × D × T)

Requires velocity update per dimension; comparable to GWO

GA

O(N × D × T) + O(N × log N)

Extra cost due to selection, crossover, mutation, and sorting for elitism

Grid Search

O(G^D)

G = number of grid points per dimension; exponential in D

GWO

O(N × D × T)

Simple position update equations; no crossover or velocity terms