Exploration and Exploitation in Symbolic Regression using Quality-Diversity and Evolutionary Strategies Algorithms
This addresses symbolic regression for researchers, but it is incremental as it combines existing methods without a new paradigm.
The paper tackled symbolic regression problems by combining genetic programming, MAP-Elites, and CMA-ES to achieve high success rates, finding exactly most of the 31 targets from literature.
By combining Genetic Programming, MAP-Elites and Covariance Matrix Adaptation Evolution Strategy, we demonstrate very high success rates in Symbolic Regression problems. MAP-Elites is used to improve exploration while preserving diversity and avoiding premature convergence and bloat. Then, a Covariance Matrix Adaptation-Evolution Strategy is used to evaluate free scalars through a non-gradient-based black-box optimizer. Although this evaluation approach is not computationally scalable to high dimensional problems, our algorithm is able to find exactly most of the $31$ targets extracted from the literature on which we evaluate it.