Metamodeling by symbolic regression and Pareto simulated annealing
نویسندگان
چکیده
The subject of this paper is a new approach to symbolic regression. Other publications on symbolic regression use genetic programming. This paper describes an alternative method based on Pareto simulated annealing. Our method is based on linear regression for the estimation of constants. Interval arithmetic is applied to ensure the consistency of a model. To prevent overfitting, we merit a model not only on predictions in the data points, but also on the complexity of a model. For the complexity, we introduce a new measure. We compare our new method with the Kriging metamodel and against a symbolic regression metamodel based on genetic programming. We conclude that Pareto-simulated-annealing-based symbolic regression is very competitive compared to the other metamodel approaches.
منابع مشابه
Tuning Simulated Annealing Using the Sequential Parameter Optimization Toolbox spot
The sequential parameter optimization (spot) package for R (R Development Core Team, 2008) is a toolbox for tuning and understanding simulation and optimization algorithms. Model-based investigations are common approaches in simulation and optimization. Sequential parameter optimization has been developed, because there is a strong need for sound statistical analysis of simulation and optimizat...
متن کاملPareto-based Cost Simulated Annealing for Multiobjective Optimization
In this paper, a multiobjective simulated annealing (MOSA) method is introduced and discussed with the multiobjective evolutionary algorithms (MOEAs). Though the simulated annealing is a very powerful search algorithm and has shown good results in various singleobjective optimization fields, it has been seldom used for the multiobjective optimization because it conventionally uses only one sear...
متن کاملStudy of simulated annealing based algorithms for multiobjective optimization of a constrained problem
In this paper, four simulated annealing based multiobjective algorithms—SMOSA, UMOSA, PSA and WMOSA have been used to solve multiobjective optimization of constrained problems with varying degree of complexity along with a new PDMOSA algorithm. PDMOSA algorithm uses a strategy of Pareto dominant based fitness in the acceptance criteria of simulated annealing and is improved. In all algorithms, ...
متن کاملSanta Fe Trail for Artificial Ant with Simulating Annealing – Preliminary Study
The paper deals with a novelty tool for symbolic regression – Analytic Programming (AP) which is able to solve various problems from the symbolic regression domain. One of tasks for it can be setting an optimal trajectory for artificial ant on Santa Fe trail which is main application of Analytic Programming in this paper. In this contribution main principles of AP are described and explained. I...
متن کامل