Comment Re:Nothing new to see here (Score 1) 90
PSO is quite closely related to genetic algorithms, and also Population Monte Carlo type of methods. In a computer simulation it probably doesn't matter all that much whether one "moves" existing particles in the search space or "generates" new ones based on the previous ones.
The choice of the objective function (for example, some kind of Bayesian posterior probability) is surely more important, and unless there is something very special in the structure of the optimization problem, I think that it's a bit silly to publish papers which test various optimization methods for a given problem and conclude that some of them perform better than the others. The results are typically dependent on a multitude of factors that cannot be controlled in the experiments (a significant one is the amount of effort one spends in finding the best optimization parameters), and do no progress science all that much, particularily if one does not have a hypothesis, and preferably also some analysis, _why_ some of the optimization methods are better than others.
By the way, here's a neat paper on the use of PMC in the global illumination (radiosity/raytracing/...) problem.
The choice of the objective function (for example, some kind of Bayesian posterior probability) is surely more important, and unless there is something very special in the structure of the optimization problem, I think that it's a bit silly to publish papers which test various optimization methods for a given problem and conclude that some of them perform better than the others. The results are typically dependent on a multitude of factors that cannot be controlled in the experiments (a significant one is the amount of effort one spends in finding the best optimization parameters), and do no progress science all that much, particularily if one does not have a hypothesis, and preferably also some analysis, _why_ some of the optimization methods are better than others.
By the way, here's a neat paper on the use of PMC in the global illumination (radiosity/raytracing/...) problem.
