Runtime Analysis of Evolutionary Algorithms via Symmetry Arguments

We use an elementary argument building on group actions to prove that the selection-free steady state genetic algorithm analyzed by Sutton and Witt (GECCO 2019) takes an expected number of $\Omega(2^n / \sqrt n)$ iterations to find any particular target search point, regardless of the population size $\mu$. This improves over the previous best lower bound of $\Omega(\exp(n^{\delta/2}))$ valid for population sizes $\mu = O(n^{1/2 - \delta})$, $0 < \delta < 1/2$.

[1]  Frank Neumann,et al.  Bioinspired computation in combinatorial optimization: algorithms and their computational complexity , 2010, GECCO '12.

[2]  Cristian S. Calude,et al.  Journal of Universal Computer Science , 1994, J. Univers. Comput. Sci..

[3]  Benjamin Doerr,et al.  Improved analysis methods for crossover-based algorithms , 2009, GECCO.

[4]  Thomas Jansen,et al.  Analyzing Evolutionary Algorithms: The Computer Science Perspective , 2012 .

[5]  Exponential Upper Bounds for the Runtime of Randomized Search Heuristics , 2020, PPSN.

[6]  Frank Harary.  The Automorphism Group of a Hypercube , 2000, J. Univers. Comput. Sci..

[7]  Andrew M. Sutton,et al.  Lower Bounds on the Runtime of Crossover-Based Algorithms via Decoupling and Family Graphs , 2019, Algorithmica.

[8]  Carsten Witt,et al.  Domino convergence: why one should hill-climb on linear functions , 2018, GECCO.

[9]  Benjamin Doerr,et al.  The Impact of Random Initialization on the Runtime of Randomized Search Heuristics , 2015, Algorithmica.

[10]  Pietro Simone Oliveto,et al.  Improved time complexity analysis of the Simple Genetic Algorithm , 2015, Theor. Comput. Sci..

[11]  Pietro Simone Oliveto,et al.  Simplified Drift Analysis for Proving Lower Bounds in Evolutionary Computation , 2008, Algorithmica.

[12]  Editors , 2003 .

[13]  Benjamin Doerr,et al.  Probabilistic Tools for the Analysis of Randomized Optimization Heuristics , 2018, Theory of Evolutionary Computation.

[14]  Thomas Bäck,et al.  Theory of Evolutionary Computation: Recent Developments in Discrete Optimization , 2020, Theory of Evolutionary Computation.

[15]  J. van Leeuwen,et al.  Theoretical Computer Science , 2003, Lecture Notes in Computer Science.

[16]  Dirk Sudholt,et al.  A New Method for Lower Bounds on the Running Time of Evolutionary Algorithms , 2011, IEEE Transactions on Evolutionary Computation.

[17]  Benjamin Doerr,et al.  Money for Nothing: Speeding Up Evolutionary Algorithms Through Better Initialization , 2015, GECCO.

[18]  Andrew M. Sutton,et al.  Lower Bounds on the Runtime of Crossover-Based Algorithms via Decoupling and Family Graphs , 2021, Algorithmica.