Theory of Evolutionary Computation
Our work focuses on applying measure theory and martingale analysis to develop new evolutionary algorithms with known properties, as well as a theoretical characterization, performance measures, and convergence and no-free-lunch analysis of evolutionary computation methods in general.
People
Babak Hodjat Collaborator babak [at] cognizant com
Alan J. Lockett Ph.D. Alumni alan lockett [at] gmail com
Risto Miikkulainen Faculty risto [at] cs utexas edu
Xin Qiu Collaborator xin qiu [at] cognizant com
Hormoz Shahrzad Masters Alumni hormoz [at] cognizant com
Publications
     [Expand to show all 16][Minimize]
Accelerating Evolution Through Gene Masking and Distributed Search 2023
Hormoz Shahrzad and Risto Miikkulainen, To Appear In Proceedings of the Genetic and Evolutionary Computation Conference, pp. 972-980, 2023. (Also arXiv:2302.06745).
Accelerating Evolution Through Gene Masking and Distributed Search 2023
Hormoz Shahrzad, Masters Thesis, Department of Computer Science, The University of Texas at Austin.
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search 2023
Xin Qiu and Risto Miikkulainen, In Proceedings of the International Conference on Machine Learning (ICML-2023), , 2023. Also arXiv:2210.14016.
Simple Genetic Operators are Universal Approximators of Probability Distributions (and other Advantages of Expressive Encodings) 2022
Elliot Meyerson, Xin Qiu, and Risto Miikkulainen, In Proceedings of the Genetic and Evolutionary Computation Conference, pp. 739--748, 2022.
A Biological Perspective on Evolutionary Computation 2021
Risto Miikkulainen and Stephanie Forrest, Nature Machine Intelligence, Vol. 3 (2021), pp. 9-15.
Effective Regularization Through Loss-Function Metalearning 2021
Santiago Gonzalez and Risto Miikkulainen, arXiv:2010.00788 (2021).
A Probabilistic Re-Formulation of No Free Lunch: Continuous Lunches Are Not Free 2017
Alan J. Lockett and Risto Miikkulainen, Evolutionary Computation, Vol. 25 (2017), pp. 503--528.
Discovering Evolutionary Stepping Stones through Behavior Domination 2017
Elliot Meyerson and Risto Miikkulainen, To Appear In Proceedings of The Genetic and Evolutionary Computation Conference (GECCO 2017), Berlin, Germany, July 2017. ACM.
Estimating the Advantage of Age-Layering in Evolutionary Algorithms 2016
Hormoz Shahrzad, Babak Hodjat, and Risto Miikkulainen, To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2016, Denver, CO) 2016.
Evolutionary Annealing: Global Optimization in Arbitrary Measure Spaces 2014
Alan J Lockett and Risto Miikkulainen, Journal of Global Optimization, Vol. 58 (2014), pp. 75-108.
A Measure-Theoretic Analysis of Stochastic Optimization 2013
Alan J. Lockett and Risto Miikkulainen, In Proceedings of the 12th International Workshop on Foundations of Genetic Algorithms (FOGA-2013) 2013. ACM Press.
Measure-Theoretic Analysis of Performance in Evolutionary Algorithms 2013
Alan J Lockett, In Proceedings of the 2013 IEEE Congress on Evolutionary Computation (CEC-2013) 2013. IEEE Press.
Neuroannealing: Martingale-Driven Optimization for Neural Networks 2013
Alan J Lockett and Risto Miikkulainen, In Proceedings of the 2013 Genetic and Evolutionary Computation Conference (GECCO-2013) 2013. ACM Press.
General-Purpose Optimization Through Information-Maximization 2012
Alan J Lockett, PhD Thesis, Department of Computer Sciences, The University of Texas at Austin. Tech Report AI12-11.
Measure-Theoretic Evolutionary Annealing 2011
Alan J. Lockett and Risto Miikkulainen, In Proceedings of the 2011 IEEE Congress on Evolutionary Computation 2011.
Real-Space Evolutionary Annealing 2011
Alan J Lockett and Risto Miikkulainen, In Proceedings of the 2011 Genetic and Evolutionary Computation Conference (GECCO-2011) 2011.
Projects
Learning Strategic Behavior in Sequential Decision Tasks 2009 - 2014
Software/Data
PyEC Python package containing source code for Evolutionary Annealing along with a number of other evolutionary and stochasti... 2011
Labs
Neural Networks