Parallel Problem Solving from Nature - PPSN XII

The information geometric optimization (IGO) flow has been introduced recently by Arnold et al. This distinguished mathematical flow on the parameter manifold of a family of search distributions constitutes a novel approach to the analysis of several randomized search heuristics, including modern evolution strategies. Besides its appealing theoretical properties, it offers the unique opportunity to approach the convergence analysis of evolution strategies in two independent steps. The first step is the analysis of the flow itself, or more precisely, the convergence of its trajectories to Dirac peaks over the optimum. In a second step it remains to study the deviation of actual algorithm trajectories from the continuous flow. The present study approaches the first problem. The IGO flow of isotropic Gaussian search distributions is analyzed on convex, quadratic fitness functions. Convergence of all trajectories to the Dirac peak over the optimum is established.

[1]  Anil K. Jain,et al.  Feature Selection: Evaluation, Application, and Small Sample Performance , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Thomas Bartz-Beielstein,et al.  Tuned data mining: a benchmark study on different tuners , 2011, GECCO '11.

[3]  Zsolt Tuza,et al.  Maximum cuts and largest bipartite subgraphs , 1993, Combinatorial Optimization.

[4]  Jean-Paul Watson,et al.  Focusing on the Individual : Why We Need New Empirical Methods for Characterizing Problem Difficulty-Position Paper , 2007 .

[5]  Yong-Hyuk Kim,et al.  A hybrid genetic algorithm for the MAX CUT problem , 2001 .

[6]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[7]  David P. Williamson,et al.  Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming , 1995, JACM.

[8]  L. Darrell Whitley,et al.  The dispersion metric and the CMA evolution strategy , 2006, GECCO.

[9]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[10]  Paul M. B. Vitányi.  How well can a graph be n-colored? , 1981, Discret. Math..

[11]  Hendrik Richter,et al.  Coupled map lattices as spatio-temporal fitness functions: Landscape measures and evolutionary optimization , 2008 .

[12]  Shankar M. Venkatesan,et al.  Approximation and Intractability Results for the Maximum Cut Problem and its Variants , 1991, IEEE Trans. Computers.

[13]  Dong-il Seo,et al.  An Information-Theoretic Analysis on the Interactions of Variables in Combinatorial Optimization Problems , 2007, Evolutionary Computation.

[14]  A. Winsor.  Sampling techniques. , 2000, Nursing times.

[15]  Federico Girosi,et al.  Training support vector machines: an application to face detection , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  David Hinkley,et al.  Bootstrap Methods: Another Look at the Jackknife , 2008 .

[17]  Heike Trautmann,et al.  Benchmarking Evolutionary Algorithms: Towards Exploratory Landscape Analysis , 2010, PPSN.

[18]  Marcus Peinado,et al.  Design and Performance of Parallel and Distributed Approximation Algorithms for Maxcut , 1997, J. Parallel Distributed Comput..

[19]  Christian L. Müller,et al.  Global Characterization of the CEC 2005 Fitness Landscapes Using Fitness-Distance Analysis , 2011, EvoApplications.

[20]  Phil Husbands,et al.  Fitness Landscapes and Evolvability , 2002, Evolutionary Computation.

[21]  R. Pinter.  Optimal layer assignment for interconnect , 1984 .

[22]  A. Atiya,et al.  Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond , 2005, IEEE Transactions on Neural Networks.

[23]  Martin Grötschel,et al.  An Application of Combinatorial Optimization to Statistical Physics and Circuit Layout Design , 1988, Oper. Res..

[24]  Russell V. Lenth,et al.  Some Practical Guidelines for Effective Sample Size Determination , 2001 .

[25]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[26]  Teofilo F. Gonzalez,et al.  P-Complete Approximation Problems , 1976, J. ACM.

[27]  Walter Daelemans,et al.  Combined Optimization of Feature Selection and Algorithm Parameters in Machine Learning of Language , 2003, ECML.

[28]  Terry Jones,et al.  Fitness Distance Correlation as a Measure of Problem Difficulty for Genetic Algorithms , 1995, ICGA.

[29]  S. Poljak,et al.  A Polynomial Algorithm for Constructing a Large Bipartite Subgraph, with an Application to a Satisfiability Problem , 1982, Canadian Journal of Mathematics.

[30]  J. Christopher Beck,et al.  Adaptive Search Algorithms and Fitness-Distance Correlation , 2003 .

[31]  Anil K. Jain,et al.  Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Richard J. Beckman,et al.  A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output From a Computer Code , 2000, Technometrics.

[33]  Bernd Bischl,et al.  Resampling Methods in Model Validation , 2010 .

[34]  Hanno Lefmann,et al.  A combinatorial design approach to MAXCUT , 1996, Random Struct. Algorithms.