03466cam a22003977 4500001000700000003000500007005001700012006001900029007001500048008004100063100002100104245008900125260006600214300005700280490004200337500001800379520149600397530006001893538007201953538003602025588002502061690006902086690008902155690008302244690011002327690012302437690010102560690006802661690010002729700002002829700002502849710004202874830007702916856003802993856003703031w26340NBER20200223002007.0m o d cr cnu||||||||200223s2019 mau fo 000 0 eng d1 aArnoud, Antoine.10aBenchmarking Global Optimizers /cAntoine Arnoud, Fatih Guvenen, Tatjana Kleineberg. aCambridge, Mass.bNational Bureau of Economic Researchc2019. a1 online resource:billustrations (black and white);1 aNBER working paper seriesvno. w26340 aOctober 2019.3 aWe benchmark seven global optimization algorithms by comparing their performance on challenging multidimensional test functions as well as a method of simulated moments estimation of a panel data model of earnings dynamics. Five of the algorithms are taken from the popular NLopt open-source library: (i) Controlled Random Search with local mutation (CRS), (ii) Improved Stochastic Ranking Evolution Strategy (ISRES), (iii) Multi-Level Single-Linkage (MLSL) algorithm, (iv) Stochastic Global Optimization (StoGo), and (v) Evolutionary Strategy with Cauchy distribution (ESCH). The other two algorithms are versions of TikTak, which is a multistart global optimization algorithm used in some recent economic applications. For completeness, we add three popular local algorithms to the comparison--the Nelder-Mead downhill simplex algorithm, the Derivative-Free Non-linear Least Squares (DFNLS) algorithm, and a popular variant of the Davidon-Fletcher-Powell (DFPMIN) algorithm. To give a detailed comparison of algorithms, we use a set of benchmarking tools recently developed in the applied mathematics literature. We find that the success rate of many optimizers vary dramatically with the characteristics of each problem and the computational budget that is available. Overall, TikTak is the strongest performer on both the math test functions and the economic application. The next-best performing optimizers are StoGo and CRS for the test functions and MLSL for the economic application. aHardcopy version available to institutional subscribers aSystem requirements: Adobe [Acrobat] Reader required for PDF files. aMode of access: World Wide Web.0 aPrint version record 7aC13 - Estimation: General2Journal of Economic Literature class. 7aC15 - Statistical Simulation Methods: General2Journal of Economic Literature class. 7aC51 - Model Construction and Estimation2Journal of Economic Literature class. 7aC53 - Forecasting and Prediction Methods • Simulation Methods2Journal of Economic Literature class. 7aC61 - Optimization Techniques • Programming Models • Dynamic Analysis2Journal of Economic Literature class. 7aC63 - Computational Techniques • Simulation Modeling2Journal of Economic Literature class. 7aD52 - Incomplete Markets2Journal of Economic Literature class. 7aJ31 - Wage Level and Structure • Wage Differentials2Journal of Economic Literature class.1 aGuvenen, Fatih.1 aKleineberg, Tatjana.2 aNational Bureau of Economic Research. 0aWorking Paper Series (National Bureau of Economic Research)vno. w26340.40uhttp://www.nber.org/papers/w2634040uhttp://dx.doi.org/10.3386/w26340