neural networks research group
areas • people • projects • demos • publications • software/data •
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.
Publications
     [Expand to show all 15][Minimize]
Accelerating Evolution Through Gene Masking and Distributed Search Hormoz Shahrzad and Risto Miikkulainen arXiv:2302.06745, 2023. 2023
Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Search Xin Qiu and Risto Miikkulainen arXiv:2210.14016( ), 2023. 2023
Simple Genetic Operators are Universal Approximators of Probability Distributions (and other Advantages of Expressive Encodings) Elliot Meyerson, Xin Qiu, and Risto Miikkulainen In Proceedings of the Genetic and Evolutionary Computation Conference, 739--748, 2022. 2022
A Biological Perspective on Evolutionary Computation Risto Miikkulainen and Stephanie Forrest Nature Machine Intelligence, 3:9-15, 2021. 2021
Effective Regularization Through Loss-Function Metalearning Santiago Gonzalez and Risto Miikkulainen In arXiv:2010.00788, 2021. 2021
Discovering Evolutionary Stepping Stones through Behavior Domination Elliot Meyerson and Risto Miikkulainen To Appear In Proceedings of The Genetic and Evolutionary Computation Conference (GECCO 2017),... 2017
A Probabilistic Re-Formulation of No Free Lunch: Continuous Lunches Are Not Free Alan J. Lockett and Risto Miikkulainen Evolutionary Computation, 25:503--528, 2017. 2017
Estimating the Advantage of Age-Layering in Evolutionary Algorithms Hormoz Shahrzad, Babak Hodjat, and Risto Miikkulainen To Appear In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2016, Denv... 2016
Evolutionary Annealing: Global Optimization in Arbitrary Measure Spaces Alan J Lockett and Risto Miikkulainen Journal of Global Optimization, 58:75-108, 2014. 2014
Neuroannealing: Martingale-Driven Optimization for Neural Networks Alan J Lockett and Risto Miikkulainen In Proceedings of the 2013 Genetic and Evolutionary Computation Conference (GECCO-2013), 2013... 2013
Measure-Theoretic Analysis of Performance in Evolutionary Algorithms Alan J Lockett In Proceedings of the 2013 IEEE Congress on Evolutionary Computation (CEC-2013), 2013. IEEE P... 2013
A Measure-Theoretic Analysis of Stochastic Optimization Alan J. Lockett and Risto Miikkulainen In Proceedings of the 12th International Workshop on Foundations of Genetic Algorithms (FOGA-2013... 2013
General-Purpose Optimization Through Information-Maximization Alan J Lockett PhD Thesis, Department of Computer Sciences, The University of Texas at Austin, 2012. Tech Report AI... 2012
Real-Space Evolutionary Annealing Alan J Lockett and Risto Miikkulainen In Proceedings of the 2011 Genetic and Evolutionary Computation Conference (GECCO-2011), 2011... 2011
Measure-Theoretic Evolutionary Annealing Alan J. Lockett and Risto Miikkulainen In Proceedings of the 2011 IEEE Congress on Evolutionary Computation, 2011. 2011
People
Alan J. Lockett Ph.D. Alumni alan lockett [at] gmail com
Risto Miikkulainen Faculty risto [at] cs utexas edu
Hormoz Shahrzad Masters Student hormoz [at] cognizant com
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
UT Only: Advice • Calendar • Admin