Filters








1,848 Hits in 2.4 sec

A discrete version of CMA-ES [article]

Eric Benhamou, Jamal Atif, Rida Laraki
2019 arXiv   pre-print
This allows creating a version of CMA ES that can accommodate efficiently discrete variables. We provide the corresponding algorithm and conclude.  ...  These strategies originated in the early 1960s, named Evolution Strategy (ES) have culminated with the CMA-ES (Covariance Matrix Adaptation) ES.  ...  Secondly, we would like to use a discrete distribution that maximizes the entropy. This is the case for the continuous version of CMA-ES with the normal distribution.  ... 
arXiv:1812.11859v2 fatcat:eaj7kotszjdv7ji5vyvwl3uk7a

A Modification of the PBIL Algorithm Inspired by the CMA-ES Algorithm in Discrete Knapsack Problem

Maria Konieczka, Alicja Poturała, Jarosław Arabas, Stanisław Kozdrowski
2021 Applied Sciences  
Strategy (CMA-ES) algorithm.  ...  The comparison of algorithms was performed in the discrete domain of the solution space, where we used the well-known knapsack problem in a variety of data correlations.  ...  The key among them is how the parameters are updated-in EDAs, learning considers a set of points, while CMA-ES considers a set of steps [10] .  ... 
doi:10.3390/app11199136 fatcat:pst6gbbg2jhj7ht2jgdxnvia6m

Covariance Matrix Adaptation Greedy Search Applied to Water Distribution System Optimization [article]

Mehdi Neshat, Bradley Alexander, Angus Simpson
2019 arXiv   pre-print
This paper proposes a new hybrid evolutionary framework that consists of three distinct phases. The first phase applied CMA-ES, a robust adaptive meta-heuristic for continuous optimisation.  ...  The results reveal that the new framework outperforms CMA-ES by itself and other previously applied heuristics on most benchmarks in terms of both optimisation speed and network cost.  ...  The main objective of the xx xxii study is evaluating the performance of the hybrid framework with discrete pipe sizes (commercialized), so the discrete results of CMA ES -GS U and CMA ES -GS U -GS D  ... 
arXiv:1909.04846v1 fatcat:yfziehhxrzam5itexmlb64lggy

An ACO algorithm benchmarked on the BBOB noiseless function testbed

Tianjun Liao, Daniel Molina, Thomas Stutzle, Marco A. Montes de Oca, Marco Dorigo
2012 Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion - GECCO Companion '12  
The latter version is competitive on the five dimensional functions to (1+1)-CMA-ES and BIPOP-CMA-ES.  ...  Furthermore, in dimension 5, we present the results of the ACO R when it uses variable correlation handling.  ...  It is observed that the latter version is competitive to (1+1)-CMA-ES and BIPOP-CMA-ES in functions with moderate or high conditioning.  ... 
doi:10.1145/2330784.2330809 dblp:conf/gecco/LiaoMSOD12 fatcat:sxg4vybsibfj5pmkyl2pmptv7m

Population-based heuristic algorithms for continuous and mixed discrete-continuous optimization problems

Tianjun Liao
2015 4OR  
(iii) we extend CMA-ES to tackle mixed discrete-continuous optimization problems.  ...  We also propose iCMAES-ILS, a hybrid algorithm that loosely couples IPOP-CMA-ES, a CMA-ES variant that uses a restart schema coupled with an increasing population iii v me to apply for a fellowship from  ...  IPOP-CMA-ES embeds CMA-ES into a restart mechanism that increases the population size between successive runs of CMA-ES.  ... 
doi:10.1007/s10288-015-0285-8 fatcat:fbdeu2lx4ngghdyqenamhfckry

Learning-assisted evolutionary search for scalable function optimization: LEM(ID3)

Guleng Sheri, David Corne
2010 IEEE Congress on Evolutionary Computation  
We describe the results, and in particular compare with the three most successful algorithms from the CEC 2005 competition; Sinha et al's K-PCX, and two versions of Auger and Hansen's CMA-ES.  ...  Inspired originally by the Learnable Evolution Model(LEM) [5], we investigate LEM(ID3), a hybrid of evolutionary search with ID3 decision tree learning.  ...  resizing) [2] , L-CMA-ES [1] (an alternative version of CMA-ES), and K-PCX [11] . a carefully designed evolutionary algorithm with a specialised crossover operator (PCX).  ... 
doi:10.1109/cec.2010.5586226 dblp:conf/cec/SheriC10 fatcat:qh7iz2tzrbat7hju37wapl4uba

Adaptive Generation-Based Evolution Control for Gaussian Process Surrogate Models [article]

Jakub Repicky, Lukas Bajer, Zbynek Pitra, Martin Holena
2017 arXiv   pre-print
The version called Surrogate CMA-ES uses Gaussian processes or random forests surrogate models with a generation-based evolution control.  ...  This paper presents an adaptive improvement for S-CMA-ES based on a general procedure introduced with the s*ACM-ES algorithm, in which the number of generations using the surrogate model before retraining  ...  Access to computing and storage facilities owned by parties and projects contributing to the National Grid Infrastructure MetaCentrum, provided under the programme "Projects of Large Research, Development  ... 
arXiv:1709.10443v1 fatcat:iwt6vfeidbd63fkgzlfohvag6u

MORE: Mixed Optimization for Reverse Engineering—An Application to Modeling Biological Networks Response via Sparse Systems of Nonlinear Differential Equations

Francesco Sambo, Marco A. Montes de Oca, Barbara Di Camillo, Gianna Toffolo, Thomas Stutzle
2012 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
Reverse engineering is the problem of inferring the structure of a network of interactions between biological variables from a set of observations.  ...  The model inferred by MORE is a sparse system of nonlinear differential equations, complex enough to realistically describe the dynamics of a biological system.  ...  -FNRS, of which he is a research associate. Francesco Sambo would like to thank Professor Silvana Badaloni for her precious advice and for letting this collaboration happen.  ... 
doi:10.1109/tcbb.2012.56 pmid:22837424 fatcat:iqi4pux4a5dazlqr6ihk6ppggq

Mixed-integer benchmark problems for single- and bi-objective optimization

Tea Tušar, Dimo Brockhoff, Nikolaus Hansen
2019 Proceedings of the Genetic and Evolutionary Computation Conference on - GECCO '19  
They contain problems of diverse difficulties that are scalable in the number of decision variables.  ...  The bbob-mixint suite is designed by partially discretizing the established BBOB (Black-Box Optimization Benchmarking) problems.  ...  The experiments were run for a budget of 10 4 n for Random Search, DE, and CMA-ES and for a budget of 50n for TPE (due its long internal runtime).  ... 
doi:10.1145/3321707.3321868 dblp:conf/gecco/TusarBH19 fatcat:vnatehfqlngjriknxtoj772hvy

Protein Conformation Motion Modeling Using Sep-CMA-ES

Maxim Buzdalov, Sergey Knyazev, Yury Porozov
2014 2014 13th International Conference on Machine Learning and Applications  
The optimization is performed using sep-CMA-ES, which makes the running time of an iteration linear in the number of amino acids in a protein.  ...  We present a new coarse-grained method of modeling the protein motion between two given conformations.  ...  Although we cannot guarantee that our problem is separable, the authors of sep-CMA-ES state [20] that for large problem dimensions their approach is competitive with the full version of CMA-ES, when  ... 
doi:10.1109/icmla.2014.12 dblp:conf/icmla/BuzdalovKP14 fatcat:tm2pgg46u5c7tdikfnrpmsejg4

Yet another but more efficient black-box adversarial attack: tiling and evolution strategies [article]

Laurent Meunier, Jamal Atif, Olivier Teytaud
2019 arXiv   pre-print
In the targeted setting, we are able to reach, with a limited budget of 100,000, 100% of success rate with a budget of 6,662 queries on average, i.e. we need 800 queries less than the current state of  ...  We introduce a new black-box attack achieving state of the art performances.  ...  then m ← m , σ ← 2σ else σ ← 2 − 1 4 σ end if end for A.2 CMA-ES ALGORITHM Algorithm 2 CMA-ES algorithm.  ... 
arXiv:1910.02244v2 fatcat:rzpkph6fcvagbhg3ydl37bgwiu

Black box optimization for automatic speech recognition

Shinji Watanabe, Jonathan Le Roux
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
: Covariance Mean Adaptation Evolution Strategy (CMA-ES) and Bayesian optimization using Gaussian process.  ...  : Covariance Mean Adaptation Evolution Strategy (CMA-ES) and Bayesian optimization using Gaussian process.  ...  We used the python version of CMA-ES 3 with some discretization for discrete tuning parameters in our implementation, and the Spearmint package for Bayesian optimization 4 .  ... 
doi:10.1109/icassp.2014.6854202 dblp:conf/icassp/WatanabeR14 fatcat:ceeduejacffmjncvesw6snthgu

A novel population-based multi-objective CMA-ES and the impact of different constraint handling techniques

Silvio Rodrigues, Pavol Bauer, Peter A.N. Bosman
2014 Proceedings of the 2014 conference on Genetic and evolutionary computation - GECCO '14  
Although several extensions of CMA-ES to multi-objective (MO) optimization exist, no extension incorporates a key component of the most robust and general CMA-ES variant: the association of a population  ...  The Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) is a well-known, state-of-the-art optimization algorithm for single-objective real-valued problems, especially in black-box settings.  ...  Therefore, we computed 5000 uniformly sampled solutions along the optimal Pareto front to use as a discretized version of PF for a high-quality approximation.  ... 
doi:10.1145/2576768.2598329 dblp:conf/gecco/RodriguesBB14 fatcat:r2q5m6yyzzfqjieyxudewkmz7i

Globally convergent evolution strategies

Y. Diouane, S. Gratton, L. N. Vicente
2014 Mathematical programming  
One relevant instance of such an ES is CMA-ES (covariance matrix adaptation ES).  ...  Given a limited budget of function evaluations, our numerical experiments have shown that the modified CMA-ES is capable of further progress in function values.  ...  Acknowledgments We would like to thank three anonymous referees, the associate editor, and the co-editor (Sven Leyffer) for their comments which improved the presentation of the paper.  ... 
doi:10.1007/s10107-014-0793-x fatcat:vciud4oslvdlfdmkjqst33wll4

Identification of the Isotherm Function in Chromatography Using CMA-ES [article]

Mohamed Jebalia, Marc Schoenauer
2007 arXiv   pre-print
CMA-ES is then applied to real data cases and its results are compared to those of a gradient-based strategy.  ...  The state-of-the-art Evolution Strategy, CMA-ES (the Covariance Matrix Adaptation Evolution Strategy), is used to identify the parameters of the so-called isotherm function.  ...  The authors would like to thank Nikolaus Hansen for the Scilab version of CMA-ES, and for his numerous useful comments.  ... 
arXiv:0710.0322v1 fatcat:hca6ojslonf4bkcwbdtl2jvugq
« Previous Showing results 1 — 15 out of 1,848 results