Benchmarking SPSA on BBOB-2010 noiseless function testbed

This paper presents the result for Simultaneous Perturbation Stochastic Approximation (SPSA) on the BBOB 2010 noiseless testbed. SPSA is a stochastic gradient approximation strategy which uses random directions for the gradient estimate. The paper describes the steps performed by the strategy and the experimental setup. The chosen setup represents a rather basic variant of SPSA. Overall the strategy is able to solve 2 of the 24 test functions. For each test function at least one target level was reached for D = 3.

[1]  J. Spall.  Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[2]  J. Spall.  Adaptive stochastic approximation by the simultaneous perturbation method , 1998, Proceedings of the 37th IEEE Conference on Decision and Control (Cat. No.98CH36171).

[3]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[4]  J. Blum.  Multidimensional Stochastic Approximation Methods , 1954 .

[5]  Anne Auger,et al.  Real-Parameter Black-Box Optimization Benchmarking 2009: Noiseless Functions Definitions , 2009 .

[6]  L. Gerencsér,et al.  The mathematics of noise-free SPSA , 2001, Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228).

[7]  N. Hansen,et al.  Real-Parameter Black-Box Optimization Benchmarking: Experimental Setup , 2010 .

[8]  James C. Spall.  Feedback and Weighting Mechanisms for Improving Jacobian Estimates in the Adaptive Simultaneous Perturbation Algorithm , 2009, IEEE Trans. Autom. Control..

[9]  L. Gerencsér,et al.  SPSA in noise free optimization , 2000, Proceedings of the 2000 American Control Conference. ACC (IEEE Cat. No.00CH36334).

[10]  James C. Spall,et al.  Introduction to stochastic search and optimization - estimation, simulation, and control , 2003, Wiley-Interscience series in discrete mathematics and optimization.