Drift Analysis with Tail Bounds

We give a simple and short alternative proof of the multiplicative drift theorem published recently (Doerr, Johannsen, Winzen (GECCO 2010)). It completely avoids the use of drift theorems previously used in the theory of evolutionary computation. By this, its proof is fully self-contained. The new theorem yields exactly the same bounds for expected runtimes as the previous theorem. In addition, it also gives good bounds on the deviations from the mean. This shows, for the first time, that the classical O(n log n) run-time bound for the (1+1) evolutionary algorithm for optimizing linear functions holds with high probability (and not just in expectation). Similar improvements are obtained for other classical problems in the evolutionary algorithms literature, for example computing minimum spanning trees, finding single-source shortest paths, and finding Eulerian cycles.

[1]  Thomas Jansen,et al.  On the analysis of the (1+1) evolutionary algorithm , 2002, Theor. Comput. Sci..

[2]  Xin Yao,et al.  Drift analysis and average time complexity of evolutionary algorithms , 2001, Artif. Intell..

[3]  Frank Neumann,et al.  Rigorous analyses of fitness-proportional selection for optimizing linear functions , 2008, GECCO '08.

[4]  Ingo Wegener,et al.  Evolutionary Algorithms and the Maximum Matching Problem , 2003, STACS.

[5]  Benjamin Doerr,et al.  Multiplicative drift analysis , 2010, GECCO.

[6]  Benjamin Doerr,et al.  Adjacency list matchings: an ideal genotype for cycle covers , 2007, GECCO '07.

[7]  Catherine S. Greenhill,et al.  Surveys in Combinatorics, 1999: Random Walks on Combinatorial Objects , 1999 .

[8]  Pietro Simone Oliveto,et al.  Erratum: Simplified Drift Analysis for Proving Lower Bounds in Evolutionary Computation , 2008, PPSN.

[9]  Ingo Wegener,et al.  The analysis of evolutionary algorithms on sorting and shortest paths problems , 2004, J. Math. Model. Algorithms.

[10]  Benjamin Doerr,et al.  A Tight Bound for the (1+1)-EA on the Single Source Shortest Path Problem , 2007 .

[11]  Benjamin Doerr,et al.  Edge-based representation beats vertex-based representation in shortest path problems , 2010, GECCO '10.

[12]  Frank Neumann,et al.  Expected runtimes of evolutionary algorithms for the Eulerian cycle problem , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[13]  Pietro Simone Oliveto,et al.  Theoretical analysis of fitness-proportional selection: landscapes and efficiency , 2009, GECCO.

[14]  G. Grimmett,et al.  Probability and random processes , 2002 .

[15]  Benjamin Doerr,et al.  Drift analysis and linear functions revisited , 2010, IEEE Congress on Evolutionary Computation.

[16]  Frank Neumann,et al.  Speeding Up Evolutionary Algorithms Through Restricted Mutation Operators , 2006, PPSN.

[17]  Xin Yao,et al.  A study of drift analysis for estimating computation time of evolutionary algorithms , 2004, Natural Computing.

[18]  Simon M. Lucas,et al.  Parallel Problem Solving from Nature - PPSN X, 10th International Conference Dortmund, Germany, September 13-17, 2008, Proceedings , 2008, PPSN.

[19]  Martin Skutella,et al.  Evolutionary Algorithms and Matroid Optimization Problems , 2007, GECCO '07.

[20]  B. Hajek.  Hitting-time and occupation-time bounds implied by drift analysis with applications , 1982, Advances in Applied Probability.

[21]  Ingo Wegener,et al.  Randomized local search, evolutionary algorithms, and the minimum spanning tree problem , 2004, Theor. Comput. Sci..

[22]  Edmund K. Burke,et al.  Parallel Problem Solving from Nature - PPSN IX: 9th International Conference, Reykjavik, Iceland, September 9-13, 2006, Proceedings , 2006, PPSN.

[23]  Benjamin Doerr,et al.  Faster Evolutionary Algorithms by Superior Graph Representation , 2007, 2007 IEEE Symposium on Foundations of Computational Intelligence.

[24]  Per Kristian Lehre,et al.  On the Effect of Populations in Evolutionary Multi-Objective Optimisation , 2006, Evolutionary Computation.

[25]  R. A. Doney,et al.  4. Probability and Random Processes , 1993 .

[26]  Frank Neumann,et al.  Computing single source shortest paths using single-objective fitness , 2009, FOGA '09.

[27]  Leslie Ann Goldberg,et al.  Adaptive Drift Analysis , 2010, PPSN.

[28]  C. Hierholzer,et al.  Ueber die Möglichkeit, einen Linienzug ohne Wiederholung und ohne Unterbrechung zu umfahren , 1873 .