ABSTRACT
The quality of candidate solutions in evolutionary computation (EC) depend on multiple independent runs and a large number of them fail to guarantee optimal result. These runs consume more or less equal or sometimes higher amount of computational resources on par the runs that produce desirable results.
This research work addresses these two issues (run quality, execution time), Run Prediction Model (RPM), in which undesirable quality evolutionary runs are identified to discontinue from their execution. An Ant Colony Optimization (ACO) based classifier that learns to discover a prediction model from the early generations of an EC run.
We consider Grammatical Evolution (GE) as our EC technique to apply RPM that is evaluated on four symbolic regression problems. We establish that the RPM applied GE produces a significant improvement in the success rate while reducing the execution time.
- G. Chennupati, C. Ryan, and R. M. A. Azad. An empirical analysis through the time complexity of GE problems. In R. Matousek, editor, 19th International Conference on Soft Computing, MENDEL'13, pages 37--44, Brno, Czech Republic, jun, 26-28 2013.Google Scholar
- D. Costelloe and C. Ryan. On improving generalisation in genetic programming. In L. Vanneschi, S. Gustafson, A. Moraglio, I. Falco, and M. Ebner, editors, Genetic Programming, volume 5481 of LNCS, pages 61--72. Springer, Berlin, Heidelberg, 2009. Google ScholarDigital Library
- M. Dorigo and T. Stützle. Ant colony optimization. MIT Press, 2004. Google ScholarCross Ref
- M. Keijzer. Improving symbolic regression with interval arithmetic and linear scaling. In C. Ryan, T. Soule, M. Keijzer, E. Tsang, R. Poli, and E. Costa, editors, Genetic Programming, volume 2610 of LNCS, pages 70--82. Springer, Berlin, Heidelberg, 2003. Google ScholarDigital Library
- D. Martens, B. Baesens, and T. Fawcett. Editorial survey: swarm intelligence for data mining. Machine Learning, 82(1):1--42, 2011. Google ScholarDigital Library
- M. Medland and F. E. B. Otero. A study of different quality evaluation functions in the cant-miner(pb) classification algorithm. In GECCO, pages 49--56, 2012. Google ScholarDigital Library
- U.-M. O'Reilly, M. Wagy, and B. Hodjat. Ec-star: A massive-scale, hub and spoke, distributed genetic programming system. In R. Riolo, E. Vladislavleva, M. D. Ritchie, and J. H. Moore, editors, Genetic Programming Theory and Practice X, Genetic and Evolutionary Computation, pages 73--85. Springer New York, 2013.Google ScholarCross Ref
- C. Ryan, M. Keijzer, and M. Cattolico. Favourable biasing of function sets using run transferable libraries. In U.-M. O'Reilly, T. Yu, R. Riolo, and B. Worzel, editors, Genetic Programming Theory and Practice II, volume 8 of Genetic Programming, pages 103--120. Springer US, 2005.Google ScholarCross Ref
Index Terms
- Predict the success or failure of an evolutionary algorithm run
Recommendations
Predict the performance of GE with an ACO based machine learning algorithm
GECCO Comp '14: Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary ComputationThe quality of the evolved solutions of an evolutionary algorithm (EA) varies across different runs and a significant percentage of runs can produce solutions of undesirable quality. These runs are a waste of computational resources, particularly in ...
Run-time systems failure prediction via proactive monitoring
ASE '11: Proceedings of the 26th IEEE/ACM International Conference on Automated Software EngineeringIn run-time evolving systems, components may evolve while the system is being operated. Unsafe run-time changes may compromise the correct execution of the entire system. Traditional design-time verification techniques difficultly cope with run-time ...
Run-time program-specific phase prediction for python programs
ManLang '18: Proceedings of the 15th International Conference on Managed Languages & RuntimesIt is well-known that a program's execution can be partitioned into different phases. Because of their impact on micro-architectural components such as caches and branch predictors, phases are an important aspect of dynamic program behavior that is ...
Comments