Optimal Parameter Choices via Precise Black-Box Analysis

In classical runtime analysis it has been observed that certain working principles of an evolutionary algorithm cannot be understood by only looking at the asymptotic order of the runtime, but that more precise estimates are needed. In this work we demonstrate that the same observation applies to black-box complexity analysis. We prove that the unary unbiased black-box complexity of the classic OneMax function class is n ln(n) -- cn ± o(n) for a constant c between 0.2539 and 0.2665. Our analysis yields a simple (1+1)-type algorithm achieving this runtime bound via a fitness-dependent mutation strength. When translated into a fixed-budget perspective, our algorithm with the same budget computes a solution that asymptotically is 13% closer to the optimum (given that the budget is at least 0.2675n).

[1]  Michèle Sebag,et al.  Extreme Value Based Adaptive Operator Selection , 2008, PPSN.

[2]  Benjamin Doerr,et al.  The unrestricted black-box complexity of jump functions , 2017, GECCO.

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

[4]  Benjamin Doerr,et al.  Multiplicative Drift Analysis , 2010, GECCO '10.

[5]  Benjamin Doerr,et al.  Black-box complexities of combinatorial problems , 2011, GECCO '11.

[6]  Thomas Jansen,et al.  UNIVERSITY OF DORTMUND REIHE COMPUTATIONAL INTELLIGENCE COLLABORATIVE RESEARCH CENTER 531 Design and Management of Complex Technical Processes and Systems by means of Computational Intelligence Methods Upper and Lower Bounds for Randomized Search Heuristics in Black-Box Optimization , 2004 .

[7]  Thomas Bäck,et al.  The Interaction of Mutation Rate, Selection, and Self-Adaptation Within a Genetic Algorithm , 1992, PPSN.

[8]  Benjamin Doerr,et al.  Fast genetic algorithms , 2017, GECCO.

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

[10]  Johannes Lengler,et al.  A General Dichotomy of Evolutionary Algorithms on Monotone Functions , 2018, IEEE Transactions on Evolutionary Computation.

[11]  Carsten Witt,et al.  Optimal Mutation Rates for the (1+λ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda $$\end{document}) EA on One , 2017, Algorithmica.

[12]  Angelika Steger,et al.  Drift Analysis and Evolutionary Algorithms Revisited , 2016, Combinatorics, Probability and Computing.

[13]  Benjamin Doerr,et al.  From black-box complexity to designing new genetic algorithms , 2015, Theor. Comput. Sci..

[14]  Benjamin Doerr,et al.  Better Runtime Guarantees via Stochastic Domination , 2018, EvoCOP.

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

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

[17]  Benjamin Doerr,et al.  Memory-restricted black-box complexity of OneMax , 2012, Inf. Process. Lett..

[18]  Thomas Jansen,et al.  Mutation Rate Matters Even When Optimizing Monotonic Functions , 2013, Evolutionary Computation.

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

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

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

[22]  Mahmoud Fouz,et al.  Quasirandom evolutionary algorithms , 2010, GECCO '10.

[23]  Hsien-Kuei Hwang,et al.  Probabilistic Analysis of the (1+1)-Evolutionary Algorithm , 2014, Evolutionary Computation.

[24]  Pietro Simone Oliveto,et al.  On the runtime analysis of generalised selection hyper-heuristics for pseudo-boolean optimisation , 2017, GECCO.

[25]  Benjamin Doerr,et al.  Analyzing Randomized Search Heuristics: Tools from Probability Theory , 2011, Theory of Randomized Search Heuristics.

[26]  Michèle Sebag,et al.  Dynamic Multi-Armed Bandits and Extreme Value-Based Rewards for Adaptive Operator Selection in Evolutionary Algorithms , 2009, LION.

[27]  Benjamin Doerr,et al.  The Unrestricted Black-Box Complexity of Jump Functions , 2016, Evolutionary Computation.

[28]  Carsten Witt,et al.  Population Size vs. Mutation Strength for the (1+λ) EA on OneMax , 2015, GECCO.

[29]  Carsten Witt,et al.  Revised analysis of the (1+1) ea for the minimum spanning tree problem , 2014, GECCO.

[30]  Benjamin Doerr,et al.  Lower bounds for the runtime of a global multi-objective evolutionary algorithm , 2013, 2013 IEEE Congress on Evolutionary Computation.

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

[32]  Per Kristian Lehre,et al.  Black-Box Search by Unbiased Variation , 2010, GECCO '10.

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

[34]  Mahmoud Fouz,et al.  Sharp bounds by probability-generating functions and variable drift , 2011, GECCO '11.

[35]  Dorian Nogneng,et al.  A new analysis method for evolutionary optimization of dynamic and noisy objective functions , 2018, GECCO.

[36]  Benjamin Doerr,et al.  k-Bit Mutation with Self-Adjusting k Outperforms Standard Bit Mutation , 2016, PPSN.

[37]  Pietro Simone Oliveto,et al.  On the runtime analysis of selection hyper-heuristics with adaptive learning periods , 2018, GECCO.

[38]  Marc Schoenauer,et al.  Rigorous Hitting Times for Binary Mutations , 1999, Evolutionary Computation.

[39]  Olivier Teytaud,et al.  Lower Bounds for Comparison Based Evolution Strategies Using VC-dimension and Sign Patterns , 2011, Algorithmica.

[40]  Dirk Sudholt,et al.  General Lower Bounds for the Running Time of Evolutionary Algorithms , 2010, PPSN.

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

[42]  Carola Doerr,et al.  Complexity Theory for Discrete Black-Box Optimization Heuristics , 2018, Theory of Evolutionary Computation.

[43]  Jonathan E. Rowe,et al.  Theoretical analysis of local search strategies to optimize network communication subject to preserving the total number of links , 2009, Int. J. Intell. Comput. Cybern..

[44]  Jens Jägersküpper,et al.  A Blend of Markov-Chain and Drift Analysis , 2008, PPSN.

[45]  Benjamin Doerr,et al.  The (1+λ) evolutionary algorithm with self-adjusting mutation rate , 2017, GECCO.

[46]  Dirk Sudholt,et al.  The choice of the offspring population size in the (1, λ) evolutionary algorithm , 2014, Theor. Comput. Sci..

[47]  Benjamin Doerr,et al.  Ranking-Based Black-Box Complexity , 2011, Algorithmica.

[48]  Benjamin Doerr,et al.  Precise Runtime Analysis for Plateaus , 2018, PPSN.

[49]  Thomas Jansen,et al.  Performance analysis of randomised search heuristics operating with a fixed budget , 2014, Theor. Comput. Sci..

[50]  Carsten Witt,et al.  Tight Bounds on the Optimization Time of a Randomized Search Heuristic on Linear Functions† , 2013, Combinatorics, Probability and Computing.