Expand description
Shuffled Complex Evolution (SCE-UA) method for global optimization.
This is a Rust implementation of Duan’s (1992) general-purpose global optimization program developed at the Department of Hydrology & Water Resources of the University of Arizona. SCE-UA searches a continuous bounded parameter space by evolving shuffled complexes of points.
§Example
use sceua::{minimize, Config};
let result = minimize(
|x| x.iter().map(|value| value * value).sum::<f64>(),
&[-5.0, -5.0],
&[5.0, 5.0],
Config::default(),
)?;
assert_eq!(result.best_x.len(), 2);Reference: Duan, Q., Sorooshian, S., and Gupta, V.K. (1992), “Effective and efficient global optimization for conceptual rainfall-runoff models”, Water Resources Research, 28(4), 1015-1031.
Modules§
- duan_
test_ func - Standard optimisation test functions from Duan’s Matlab SCE-UA suite.
Structs§
- Config
- SCE-UA algorithmic control and convergence-check parameters.
- History
Entry - Population summary recorded after shuffling loops.
- Optimization
Result - Final parameter estimate, criterion value, and search metadata.
Enums§
- Sceua
Error - Errors returned by the SCE-UA optimizer.
- Termination
Reason - Search termination condition.
Functions§
- minimize
- Run the Shuffled Complex Evolution method for global optimization.