Improved Fixed-Budget Results via Drift Analysis

Fixed-budget theory is concerned with computing or bounding the fitness value achievable by randomized search heuristics within a given budget of fitness function evaluations. Despite recent progress in fixed-budget theory, there is a lack of general tools to derive such results. We transfer drift theory, the key tool to derive expected optimization times, to the fixed-budged perspective. A first and easy-to-use statement concerned with iterating drift in so-called greed-admitting scenarios immediately translates into bounds on the expected function value. Afterwards, we consider a more general tool based on the well-known variable drift theorem. Applications of this technique to the LeadingOnes benchmark function yield statements that are more precise than the previous state of the art.

[1]  Thomas Jansen,et al.  A method to derive fixed budget results from expected optimisation times , 2013, GECCO '13.

[2]  Timo Kötzing Concentration of First Hitting Times Under Additive Drift , 2015, Algorithmica.

[3]  Per Kristian Lehre,et al.  Concentrated Hitting Times of Randomized Search Heuristics with Variable Drift , 2014, ISAAC.

[4]  Pietro Simone Oliveto,et al.  On the impact of the cutoff time on the performance of algorithm configurators , 2019, GECCO.

[5]  Thomas Jansen,et al.  Reevaluating Immune-Inspired Hypermutations Using the Fixed Budget Perspective , 2014, IEEE Transactions on Evolutionary Computation.

[6]  Christine Zarges,et al.  Unlimited Budget Analysis of Randomised Search Heuristics , 2019, ArXiv.

[7]  M. Wainwright Basic tail and concentration bounds , 2019, High-Dimensional Statistics.

[8]  Xiequan Fan,et al.  Exponential inequalities for martingales with applications , 2013, 1311.6273.

[9]  M. Habib Probabilistic methods for algorithmic discrete mathematics , 1998 .

[10]  Benjamin Doerr,et al.  Optimal Parameter Choices via Precise Black-Box Analysis , 2016, GECCO.

[11]  Johannes Lengler,et al.  Fixed Budget Performance of the (1+1) EA on Linear Functions , 2015, FOGA.

[12]  Hsien-Kuei Hwang,et al.  Sharp bounds on the runtime of the (1+1) EA via drift analysis and analytic combinatorial tools , 2019, FOGA '19.

[13]  Thomas Jansen,et al.  Fixed budget computations: a different perspective on run time analysis , 2012, GECCO '12.

[14]  Frank Neumann,et al.  Optimal Fixed and Adaptive Mutation Rates for the LeadingOnes Problem , 2010, PPSN.

[15]  Per Kristian Lehre,et al.  Drift analysis , 2012, GECCO '12.

[16]  Thomas Jansen,et al.  Analysing Stochastic Search Heuristics Operating on a Fixed Budget , 2019, Theory of Evolutionary Computation.

[17]  Daniel Johannsen,et al.  Random combinatorial structures and randomized search heuristics , 2010 .

[18]  Dirk Sudholt,et al.  Expected Fitness Gains of Randomized Search Heuristics for the Traveling Salesperson Problem , 2016, Evolutionary Computation.