Filters








22 Hits in 4.8 sec

Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed

Nikolaus Hansen
2009 Proceedings of the 11th annual conference companion on Genetic and evolutionary computation conference - GECCO '09  
This BI-population CMA-ES is benchmarked on the BBOB-2009 noiseless function testbed and could solve 23, 22 and 20 functions out of 24 in search space dimensions 10, 20 and 40, respectively, within a budget  ...  We 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.  ...  CONCLUSION The BI-population CMA-ES performs satisfactorily on many functions of the BBOB-2009 testbed and exhibits a reasonable scaling behavior: between linear and quadratic on unimodal functions, between  ... 
doi:10.1145/1570256.1570333 dblp:conf/gecco/Hansen09 fatcat:aphvj7hdsnh5dlcxoqzm75kj5u

Benchmarking a weighted negative covariance matrix update on the BBOB-2010 noisy testbed

Nikolaus Hansen, Raymond Ros
2010 Proceedings of the 12th annual conference comp on Genetic and evolutionary computation - GECCO '10  
In this paper, we benchmark the IPOP-aCMA-ES on the BBOB-2010 noisy testbed in search space dimension between 2 and 40 and compare its performance with the IPOP-CMA-ES.  ...  Compared to the best performance observed during BBOB-2009, the IPOP-aCMA-ES sets a new record on overall ten functions.  ...  Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed. In Rothlauf [14], pages 2389-2396. [4] N. Hansen. Benchmarking a BI-population CMA-ES on the BBOB-2009 noisy testbed.  ... 
doi:10.1145/1830761.1830789 dblp:conf/gecco/HansenR10b fatcat:6fdns3az2bh3jbjemefcn4lc7m

Benchmarking a weighted negative covariance matrix update on the BBOB-2010 noiseless testbed

Nikolaus Hansen, Raymond Ros
2010 Proceedings of the 12th annual conference comp on Genetic and evolutionary computation - GECCO '10  
We benchmark the IPOP-aCMA-ES and compare the performance with the IPOP-CMA-ES on the BBOB-2010 noiseless testbed in dimensions between 2 and 40.  ...  On two and five functions, IPOP-CMA-ES and IPOP-aCMA-ES respectively exceed the record observed during BBOB-2009.  ...  [5Journal of Heuristics, 15(6):617-644, 2009. [6] N. Hansen. Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed. In Rothlauf [17], pages 2389-2396. [7] N. Hansen, A.  ... 
doi:10.1145/1830761.1830788 dblp:conf/gecco/HansenR10a fatcat:mqknfrk4hvf5hjir3o7pomsefq

Black-box optimization benchmarking the IPOP-CMA-ES on the noiseless testbed

Raymond Ros
2010 Proceedings of the 12th annual conference comp on Genetic and evolutionary computation - GECCO '10  
We benchmark the Covariance Matrix Adaptation-Evolution Strategy (CMA-ES) algorithm with an Increasing POPulation size (IPOP) restart policy on the BBOB noiseless testbed.  ...  The IPOP-CMA-ES is compared to the BIPOP-CMA-ES and is shown to perform at best two times faster on multi-modal functions f15 to f19 whereas it does not solve weakly structured functions f22, f23 and f24  ...  Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed. In F. Rothlauf, editor, GECCO (Companion), pages 2389-2396. ACM, 2009.  ... 
doi:10.1145/1830761.1830766 dblp:conf/gecco/Ros10b fatcat:gv65jj26ozaulpadrqtpddq5zm

Benchmarking a BI-population CMA-ES on the BBOB-2009 noisy testbed

Nikolaus Hansen
2009 Proceedings of the 11th annual conference companion on Genetic and evolutionary computation conference - GECCO '09  
We benchmark the BI-population CMA-ES on the BBOB-2009 noisy functions testbed.  ...  The latter is presumably of little use on a noisy testbed. The BI-population CMA-ES could solve 29, 27 and 26 out of 30 functions in search space dimension 5, 10 and 20 respectively.  ...  Acknowledgments The author would like to acknowledge the great and hard work of the BBOB team with particular kudos to Raymond Ros, Steffen Finck and Anne Auger, and Anne Auger and Marc Schoenauer for  ... 
doi:10.1145/1570256.1570334 dblp:conf/gecco/Hansen09a fatcat:phio3mrtyneltc6xmza4324p3u

Comparing the (1+1)-CMA-ES with a mirrored (1+2)-CMA-ES with sequential selection on the noiseless BBOB-2010 testbed

Anne Auger, Dimo Brockhoff, Nikolaus Hansen
2010 Proceedings of the 12th annual conference comp on Genetic and evolutionary computation - GECCO '10  
On the non-separable ellipsoid function in dimension 10, 20 and 40, the performances of the (1+2 s m )-CMA-ES are better by 17% than the best performance among algorithms tested during BBOB-2009 (for target  ...  12% on the sphere function.  ...  The (1+1)-CMA-ES implementing an independent restart mechanism was benchmarked for the BBOB-2009 workshop on the noiseless and noisy testbed [3, 4] .  ... 
doi:10.1145/1830761.1830771 dblp:conf/gecco/AugerBH10 fatcat:wlfquz4a35agdns4d7etm2pioa

Black-box optimization benchmarking of NIPOP-aCMA-ES and NBIPOP-aCMA-ES on the BBOB-2012 noiseless testbed

Ilya Loshchilov, Marc Schoenauer, Michele Sebag
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion - GECCO Companion '12  
We compared new strategies to CMA-ES with IPOP and BIPOP restart schemes, two algorithms with one of the best overall performance observed during the BBOB-2009 and BBOB-2010.  ...  We also present the first benchmarking of BIPOP-CMA-ES with the weighted active covariance matrix update (BIPOP-aCMA-ES).  ...  Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed. In F. Rothlauf, editor, GECCO (Companion), pages 2389-2396. ACM, 2009.  ... 
doi:10.1145/2330784.2330823 dblp:conf/gecco/LoshchilovSS12c fatcat:2ezbjwczkraz5l72rekjf37kfu

Comparison of cauchy EDA and BIPOP-CMA-ES algorithms on the BBOB noiseless testbed

Petr Pošík
2010 Proceedings of the 12th annual conference comp on Genetic and evolutionary computation - GECCO '10  
Estimation-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  ...  The two algorithms selected for the comparison are: • The bi-population variant of the evolutionary strategy with covariance matrix adaptation (BIPOP-CMA-ES) [2] which belongs to the best algorithms of  ...  Acknowledgements The author is supported by the Grant Agency of the Czech Republic with the grant no. 102/08/P094 entitled "Machine learning methods for solution construction in evolutionary algorithms  ... 
doi:10.1145/1830761.1830791 dblp:conf/gecco/Posik10 fatcat:f4vgz7bofjdnzj4gcycngpiuly

Black-box optimization benchmarking of NEWUOA compared to BIPOP-CMA-ES

Nikolaus Hansen, Raymond Ros
2010 Proceedings of the 12th annual conference comp on Genetic and evolutionary computation - GECCO '10  
The two algorithms were benchmarked on the BBOB 2009 noiseless function testbed.  ...  Nevertheless, BIPOP-CMA-ES is faster and has a better success probability than NEWUOA in reaching target function values smaller than one on all other functions.  ...  For benchmarking NEWUOA on the BBOB 2009 noiseless function testbed, an independent multi-start procedure had been implemented as advised in [5] .  ... 
doi:10.1145/1830761.1830768 dblp:conf/gecco/HansenR10 fatcat:kao4lgkbo5fungt2dcseiwfka4

Black-box optimization benchmarking of IPOP-saACM-ES and BIPOP-saACM-ES on the BBOB-2012 noiseless testbed

Ilya Loshchilov, Marc Schoenauer, Michele Sebag
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion - GECCO Companion '12  
We compared surrogate-assisted algorithms with their surrogateless versions IPOP-aCMA-ES and BIPOP-CMA-ES, two algorithms with one of the best overall performance observed during the BBOB-2009 and BBOB  ...  The comparison shows that the surrogate-assisted versions outperform the original CMA-ES algorithms by a factor from 2 to 4 on 8 out of 24 noiseless benchmark problems, showing the best results among all  ...  Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed.  ... 
doi:10.1145/2330784.2330811 dblp:conf/gecco/LoshchilovSS12a fatcat:rvjyb6mxbbbbjen6qsilcgjciu

Black-box optimization benchmarking of IPOP-saACM-ES and BIPOP-saACM-ES on the BBOB-2012 noiseless testbed [article]

Ilya Loshchilov, Marc Schoenauer (INRIA Saclay - Ile de France, MSR - INRIA), Michèle Sebag (INRIA Saclay - Ile de France, LRI)
2012 arXiv   pre-print
The comparison shows that the surrogate-assisted versions outperform the original CMA-ES algorithms by a factor from 2 to 4 on 8 out of 24 noiseless benchmark problems, showing the best results among all  ...  algorithms of the BBOB-2009 and BBOB-2010 on Ellipsoid, Discus, Bent Cigar, Sharp Ridge and Sum of different powers functions.  ...  Benchmarking a BI-population CMA-ES on the BBOB-2009 function testbed.  ... 
arXiv:1206.5780v1 fatcat:kjje6spxlreupfd7gks34mgpea

Benchmarking Numerical Multiobjective Optimizers Revisited

Dimo Brockhoff, Thanh-Do Tran, Nikolaus Hansen
2015 Proceedings of the 2015 on Genetic and Evolutionary Computation Conference - GECCO '15  
We apply this approach to compare three common algorithms on a new test function suite derived from the well-known single-objective BBOB functions.  ...  The focus thereby lies less on gaining insights into the algorithms but more on showcasing the concepts and on what can be gained over current benchmarking approaches.  ...  Acknowledgments This work was supported by the grant ANR-12-MONU-0009 (NumBBO) of the French National Research Agency. TDT is further supported by an individual PhD grant of Inria.  ... 
doi:10.1145/2739480.2754777 dblp:conf/gecco/BrockhoffTH15 fatcat:j3hnznno6ncoth4sfx4mbl5pfa

Benchmarking GNN-CMA on the BBOB testbed - pdf and data [article]

Louis Faury
2019 Zenodo  
PDF and data of the submission to GECCO's BBOB workshop.  ...  We run IPOP-CMA-ES and GNN-CMA-ES both with a budget of 10 4 × D on the BBOB 2018 noiseless function suites in four different dimensions (D=2,3,5 and 10).  ...  greatly varies among the different objective functions of the BBOB testbed.  ... 
doi:10.5281/zenodo.2640390 fatcat:hecr4cbvdrg7vigyhe3iugknra

Bi-population CMA-ES agorithms with surrogate models and line searches

Ilya Loshchilov, Marc Schoenauer, Michele Sèbag
2013 Proceeding of the fifteenth annual conference companion on Genetic and evolutionary computation conference companion - GECCO '13 Companion  
All algorithms were tested on the noiseless BBOB testbed using restarts till a total number of function evaluations of 10 6 n was reached, where n is the dimension of the function search space.  ...  First, to address expensive optimization, we benchmark a recently proposed extension of the self-adaptive surrogate-assisted CMA-ES which benefits from more intensive surrogate model exploitation (BIPOP-saACM-k  ...  budget of function evaluations and for these dimensions is better than of all algorithms tested during the BBOB-2009, BBOB-2010 and BBOB-2012.  ... 
doi:10.1145/2464576.2482696 dblp:conf/gecco/LoshchilovSS13a fatcat:lbqteveifza4rcpc667aq4hpvy

The Hessian Estimation Evolution Strategy [article]

Tobias Glasmachers, Oswin Krause
2020 arXiv   pre-print
We demonstrate that our approach to covariance matrix adaptation is efficient by evaluation it on the BBOB/COCO testbed.  ...  For this, we extend the cumulative step-size adaptation algorithm of the CMA-ES to mirrored sampling.  ...  Our first experiment is to run the standardized BBOB/COCO procedure, which tests the algorithm on 15 instances of 24 benchmark problems [6] .  ... 
arXiv:2003.13256v2 fatcat:2zm5osakzrcgrnjr6bfed2btaq
« Previous Showing results 1 — 15 out of 22 results