2000 character limit reached
Runtime Analysis of Competitive co-Evolutionary Algorithms for Maximin Optimisation of a Bilinear Function (2206.15238v2)
Published 30 Jun 2022 in cs.NE and q-bio.PE
Abstract: Co-evolutionary algorithms have a wide range of applications, such as in hardware design, evolution of strategies for board games, and patching software bugs. However, these algorithms are poorly understood and applications are often limited by pathological behaviour, such as loss of gradient, relative over-generalisation, and mediocre objective stasis. It is an open challenge to develop a theory that can predict when co-evolutionary algorithms find solutions efficiently and reliable. This paper provides a first step in developing runtime analysis for population-based competitive co-evolutionary algorithms. We provide a mathematical framework for describing and reasoning about the performance of co-evolutionary processes. An example application of the framework shows a scenario where a simple co-evolutionary algorithm obtains a solution in polynomial expected time. Finally, we describe settings where the co-evolutionary algorithm needs exponential time with overwhelmingly high probability to obtain a solution.
- On the application of Danskin’s theorem to derivative-free minimax problems. AIP Conference Proceedings, 2070(1):020026, February 2019. Publisher: American Institute of Physics.
- A novel co-evolutionary approach to automatic software bug fixing. In 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence), pages 162–168, June 2008. ISSN: 1941-0026.
- Handbook of Evolutionary Computation. IOP Publishing Ltd., GBR, 1st edition, 1997.
- Level-Based Analysis of Genetic Algorithms and Other Search Processes. IEEE Transactions on Evolutionary Computation, 22(5):707–719, October 2018.
- Theory Driven Design of Efficient Genetic Algorithms for a Classical Graph Problem. In Recent Developments in Metaheuristics, Operations Research/Computer Science Interfaces Series, pages 125–140. Springer, Cham, 2018.
- Escaping Local Optima with Non-Elitist Evolutionary Algorithms. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14):12275–12283, May 2021. Number: 14.
- Non-elitist evolutionary algorithms excel in fitness landscapes with sparse deceptive regions and dense valleys. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’21, pages 1133–1141, New York, NY, USA, June 2021. Association for Computing Machinery.
- Runtime Analysis of Non-elitist Populations: From Classical Optimisation to Partial Information. Algorithmica, 75(3):428–461, July 2016.
- Benjamin Doerr. Theory of Evolutionary Computation, chapter Probabilistic Tools for the Analysis of Randomized Optimization Heuristics, pages 1–87. Springer, Cham., 2020.
- Benjamin Doerr and Frank Neumann, editors. Theory of Evolutionary Computation. Springer, 2020.
- Upper and Lower Bounds for Randomized Search Heuristics in Black-Box Optimization. Theory of Computing Systems, 39(4):525–544, July 2006.
- Runtime analysis of a co-evolutionary algorithm: Overcoming negative drift in maximin-optimisation. In Proceedings of the 17th ACM/SIGEVO Conference on Foundations of Genetic Algorithms, FOGA ’23, pages 73–83, New York, NY, USA, 2023. Association for Computing Machinery.
- Finding Approximate Nash Equilibria of Bimatrix Games via Payoff Queries. ACM Trans. on Economics and Computation, 4(4):1–19, August 2016.
- Sevan G Ficici. Solution Concepts in Coevolutionary Algorithms. PhD thesis, Brandeis University, 2004.
- How fitness aggregation methods affect the performance of competitive coeas on bilinear problems. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’23, pages 1593–1601, New York, NY, USA, 2023. Association for Computing Machinery.
- W. Daniel Hillis. Co-evolving parasites improve simulated evolution as an optimization procedure. Physica D: Nonlinear Phenomena, 42(1):228–234, June 1990.
- The Cooperative Coevolutionary (1+1) EA. Evolutionary Computation, 12(4):405–434, December 2004.
- Mikkel T. Jensen. A New Look at Solving Minimax Problems with Coevolutionary Genetic Algorithms. In Mauricio G. C. Resende and Jorge Pinho de Sousa, editors, Metaheuristics: Computer Decision-Making, Applied Optimization, pages 369–384. Springer US, Boston, MA, 2004.
- Per Kristian Lehre. Negative Drift in Populations. In Proceedings of the 11th International Conference on Parallel Problem Solving from Nature (PPSN 2010), volume 6238 of LNCS, pages 244–253. Springer Berlin / Heidelberg, 2010.
- Per Kristian Lehre. Fitness-levels for non-elitist populations. Proceedings of the 13th annual conference on Genetic and evolutionary computation - GECCO ’11, page 2075, 2011.
- Analysis of a pairwise dominance coevolutionary algorithm and defendit. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’23, pages 1027–1035, New York, NY, USA, 2023. Association for Computing Machinery.
- Per Kristian Lehre and Phan Trung Hai Nguyen. Improved Runtime Bounds for the Univariate Marginal Distribution Algorithm via Anti-concentration. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’17, pages 1383–1390, New York, NY, USA, 2017. ACM.
- Adaptive scenario subset selection for min-max black-box continuous optimization. In Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’21, pages 697–705, New York, NY, USA, June 2021. Association for Computing Machinery.
- Randomized Algorithms. Cambridge University Press, 1995.
- Gabriela Ochoa. Error Thresholds in Genetic Algorithms. Evolutionary Computation, 14(2):157–182, June 2006.
- Adversarial genetic programming for cyber security: a rising application domain where GP matters. Genetic Programming and Evolvable Machines, 21(1-2):219–250, June 2020.
- Three Generations of Automatically Designed Robots. Artificial Life, 7(3):215–223, July 2001.
- Coevolutionary Principles. In Grzegorz Rozenberg, Thomas Bäck, and Joost N. Kok, editors, Handbook of Natural Computing, pages 987–1033. Springer Berlin Heidelberg, Berlin, Heidelberg, 2012.
- Mitchell A. Potter and Kenneth A. De Jong. Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents. Evolutionary Computation, 8(1):1–29, March 2000.
- Coevolutionary Dynamics in a Minimal Substrate. In Proceedings of the 3rd Annual Conference on Genetic and Evolutionary Computation, GECCO’01, pages 702–709, San Francisco, CA, USA, 2001. Morgan Kaufmann Publishers Inc. event-place: San Francisco, California.
- Ingo Wegener. Methods for the Analysis of Evolutionary Algorithms on Pseudo-Boolean Functions. In Ruhul Sarker, Masoud Mohammadian, and Xin Yao, editors, Evolutionary Optimization, pages 349–369. Springer US, Boston, MA, 2002.
