poli.objective_repository.toy_continuous_problem.definitions#
Defines several continuous toy problems.
This script defines all the artificial landscapes with signature [np.ndarray] -> np.ndarray. You might see that the signs have been flipped from [1] or [2]. This is because we’re dealing with maximizations instead of minimizations.
- [1] Ali R. Al-Roomi (2015). Unconstrained Single-Objective Benchmark
Functions Repository [https://www.al-roomi.org/benchmarks/unconstrained]. Halifax, Nova Scotia, Canada: Dalhousie University, Electrical and Computer Engineering.
- [2] Surjanovic, S. and Bingham, D. Virtual Library of Simulation Experiments:
Test Functions and Datasets. [https://www.sfu.ca/~ssurjano/optimization.html]
Functions
|
|
|
|
|
|
|
The 2D Branin function. |
|
|
|
Taken directly from the LineBO repository [1]. |
|
Cross-in-tray has several local maxima in a quilt-like pattern. |
|
|
|
|
|
|
|
Easom is very flat, with a maxima at (pi, pi). |
|
The egg holder is especially difficult. |
|
The 6 dimensional Hartmann function. |
|
Compute the Levy function. |
|
Compute the Rosenbrock function. |
The usual squared norm, but shifted away from the origin by a bit. |
|
|
This function is maximized at (-2.903534, ..., -2.903534), with a value of -39.16599 * d. |