Neuromemetic Evolutionary Optimization
[ 1 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ P ] employee
2020
chapter in monograph / paper
english
- optimization
- neural networks
- program synthesis
EN Discrete and combinatorial optimization can be notoriously difficult due to complex and rugged characteristics of the objective function. We address this challenge by mapping the search process to a continuous space using recurrent neural networks. Alongside with an evolutionary run, we learn three mappings: from the original search space to a continuous Cartesian latent space, from that latent space back to the search space, and from the latent space to the search objective. We elicit gradient from that last network and use it to perform moves in the latent space, and apply this Neuromemetic Evolutionary Optimization (NEO) to evolutionary synthesis of programs. Evaluation on a range of benchmarks suggests that NEO significantly outperforms conventional genetic programming.
31.08.2020
623 - 636
20
140