Yin Yang Pair Optimization (YYPO)

Single Objective YYPO (Termination Criterion: Number of Functional Evaluations)

Yin-Yang-Pair Optimization (YYPO) is a meta-heuristic optimization technique and is based on maintaining a balance between exploration and exploitation of the search space. It is a low complexity stochastic algorithm which works with two points and generates additional points depending on the number of decision variables in the optimization problem. The termination criterion employed in this code is the maximum number of functional evaluations.

It might be easier for beginners to understand YYPO with the termination criterion as maximum iterations rather than maximum functional evaluations.
The code for YYPO with the termination criteria as number of iterations is available at the following link
https://in.mathworks.com/matlabcentral/fileexchange/65556-yin-yang-pair-optimization

A p-coded GUI (along with its execution on CEC2013 functions) can be downloaded from https://goo.gl/aLXuM5

Note:
(i) The fitness function should be able to evaluate the fitness function for a set of points and not just a single point.
(ii) If D is the dimension of the problem, exactly 4D functional evaluations are required in a complete iteration of YYPO.
(iii) If T is the number of iterations, the total number of functional evaluations used in YYPO is 4DT + 2.
(iv) YYPO has three user defined parameters, viz., (i) Imin, (ii) Imax and (iii) alpha.
(v) YYPO does not employ a population and works with two points.
(vi) YYPO inherently scales the variables to 0 and 1.
(vii) YYPO is not monotonically convergent with respect to each iteration but is monotonically convergent with respect to each archive update. However, it does not lose the best determined solution due to the Archive. This code keeps track of the best solution discovered (till a particular iteration) to depict monotonic convergence.

Refer to the following article for additional details.
Yin-Yang-pair Optimization: A novel lightweight optimization algorithm
http://www.sciencedirect.com/science/article/pii/S0952197616300811
https://doi.org/10.1016/j.engappai.2016.04.004