ABSTRACT
We evaluate in this paper the GNN-CMA-ES algorithm on the BBOB noiseless testbed. The GNN-CMA-ES algorithm was recently proposed as a plug-in extension to CMA-ES, introducing the possibility to train flexible search distributions, in contrast to standard search distributions (such as the multivariate Gaussian). By comparing GNN-CMA-ES and CMA-ES, we show the benefits of this extension on some unimodal functions as well as on a variety of multimodal functions. We also identify a family of unimodal functions where GNN-CMA-ES can degrade the performances of CMA-ES and discuss the possible reasons behind this behavior.
- Anne Auger and Nikolaus Hansen. 2005. A restart CMA evolution strategy with increasing population size. In 2005 IEEE congress on evolutionary computation, Vol. 2. IEEE, 1769--1776.Google Scholar
- Joshua V Dillon, Ian Langmore, Dustin Tran, Eugene Brevdo, Srinivas Vasudevan, Dave Moore, Brian Patton, Alex Alemi, Matt Hoffman, and Rif A Saurous. 2017. Tensorflow distributions. arXiv preprint arXiv:1711.10604 (2017).Google Scholar
- Laurent Dinh, David Krueger, and Yoshua Bengio. 2014. NICE: Non-Linear Independent Components Estimation. arXiv preprint arXiv:1410.8516 (2014).Google Scholar
- Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. 2016. Density Estimation using Real NVP. arXiv preprint arXiv:1605.08803 (2016).Google Scholar
- Louis Faury, Clement Calauzenes, Olivier Fercoq, and Syrine Krichen. 2019. Improving Evolutionary Strategies with Generative Neural Networks. arXiv preprint arXiv:1901.11271 (2019).Google Scholar
- S. Finck, N. Hansen, R. Ros, and A. Auger. 2009. Real-Parameter Black-Box Optimization Benchmarking 2009: Presentation of the Noiseless Functions. Technical Report 2009/20. Research Center PPE. http://coco.lri.fr/downloads/download15.03/bbobdocfunctions.pdf Updated February 2010.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems. 2672--2680. Google ScholarDigital Library
- Nikolaus Hansen. 2016. The CMA Evolution Strategy: A tutorial. arXiv preprint arXiv:1604.00772 (2016).Google Scholar
- Nikolaus Hansen, Youhei Akimoto, and Petr Baudis. 2019. CMA-ES/pycma on Github. Zenodo, (Feb. 2019).Google Scholar
- N. Hansen, A Auger, D. Brockhoff, D. Tušar, and T. Tušar. 2016. COCO: Performance Assessment. ArXiv e-prints arXiv:1605.03560 (2016).Google Scholar
- N. Hansen, A. Auger, S. Finck, and R. Ros. 2012. Real-Parameter Black-Box Optimization Benchmarking 2012: Experimental Setup. Technical Report. INRIA. http://coco.gforge.inria.fr/bbob2012-downloadsGoogle Scholar
- N. Hansen, A. Auger, O. Mersmann, T. Tušar, and D. Brockhoff. 2016. COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting. ArXiv e-prints arXiv: 1603.08785 (2016).Google Scholar
- N. Hansen, S. Finck, R. Ros, and A. Auger. 2009. Real-Parameter Black-Box Optimization Benchmarking 2009: Noiseless Functions Definitions. Technical Report RR-6829. INRIA. http://coco.lri.fr/downloads/download15.03/bbobdocfunctions.pdf Updated February 2010.Google Scholar
- Nikolaus Hansen and Andreas Ostermeier. 2001. Completely Derandomized Self-Adaptation in Evolution Strategies. Evolutionary Computation 9, 2 (2001), 159--195. Google ScholarDigital Library
- N. Hansen, T. Tušar, O. Mersmann, A. Auger, and D. Brockhoff. 2016. COCO: The Experimental Procedure. ArXiv e-prints arXiv:1603.08776 (2016).Google Scholar
- Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- David JC MacKay. 1995. Bayesian neural networks and density networks. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment 354, 1 (1995), 73--80.Google ScholarCross Ref
- Kenneth Price. 1997. Differential evolution vs. the functions of the second ICEO. In Proceedings of the IEEE International Congress on Evolutionary Computation. 153--157.Google Scholar
- Ingo Rechenberg. 1978. Evolutionsstrategien. In Simulationsmethoden in der Medizin und Biologie. Springer, 83--114.Google Scholar
- Oren Rippel and Ryan Prescott Adams. 2013. High-dimensional Probability Estimation with Deep Density Models. arXiv preprint arXiv:1302.5125 (2013).Google Scholar
- John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017).Google Scholar
- Hans-Paul Schwefel. 1977. Numerische Optimierung von Computer-Modellen mittels der Evolutionsstrategie: mit einer vergleichenden Einführung in die Hill-Climbing-und Zufallsstrategie. Birkhäuser.Google Scholar
- Adith Swaminathan and Thorsten Joachims. 2015. Counterfactual Risk Minimization: Learning from Logged Bandit Feedback. In International Conference on Machine Learning. 814--823. Google ScholarDigital Library
- Daan Wierstra, Tom Schaul, Jan Peters, and Juergen Schmidhuber. 2008. Natural Evolution Strategies. In Evolutionary omputation, 2008. CEC 2008. (IEEE World Congress on Computational Intelligence). IEEE, 3381--3387.Google Scholar
- Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist Reinforcement Learning. Machine Learning 8, 3--4 (1992), 229--256. Google ScholarDigital Library
Index Terms
- Benchmarking GNN-CMA-ES on the BBOB noiseless testbed
Recommendations
Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed
GECCO '09: Proceedings of the 11th Annual Conference Companion on Genetic and Evolutionary Computation Conference: Late Breaking PapersWe propose a multistart CMA-ES with equal budgets for two interlaced restart strategies, one with an increasing population size and one with varying small population sizes. This BI-population CMA-ES is benchmarked on the BBOB-2009 noiseless function ...
Comparison of cauchy EDA and BIPOP-CMA-ES algorithms on the BBOB noiseless testbed
GECCO '10: Proceedings of the 12th annual conference companion on Genetic and evolutionary computationEstimation-of-distribution algorithm using Cauchy sampling distribution is compared with the bi-population CMA evolutionary strategy which was one of the best contenders in the black-box optimization benchmarking workshop in 2009. The results clearly ...
Black-box optimization benchmarking of IPOP-saACM-ES and BIPOP-saACM-ES on the BBOB-2012 noiseless testbed
GECCO '12: Proceedings of the 14th annual conference companion on Genetic and evolutionary computationIn this paper, we study the performance of IPOP-saACM-ES and BIPOP-saACM-ES, recently proposed self-adaptive surrogate-assisted Covariance Matrix Adaptation Evolution Strategies. Both algorithms were tested using restarts till a total number of function ...
Comments