Bentley, Peter J;
Lim, Soo Ling;
Gaier, Adam;
Tran, Linh;
(2022)
COIL: Constrained optimization in learned latent space: learning representations for valid solutions.
In: Fieldsend, Jonathan E and Wagner, Markus, (eds.)
GECCO '22: Proceedings of the Genetic and Evolutionary Computation Conference Companion.
(pp. pp. 1870-1877).
Association for Computing Machinery (ACM): New York, NY, USA.
Preview |
Text
3520304.3533993.pdf - Published Version Download (1MB) | Preview |
Abstract
Constrained optimization problems can be difficult because their search spaces have properties not conducive to search, e.g., multimodality, discontinuities, or deception. To address such difficulties, considerable research has been performed on creating novel evolutionary algorithms or specialized genetic operators. However, if the representation that defined the search space could be altered such that it only permitted valid solutions that satisfied the constraints, the task of finding the optimal would be made more feasible without any need for specialized optimization algorithms. We propose Constrained Optimization in Latent Space (COIL), which uses a VAE to generate a learned latent representation from a dataset comprising samples from the valid region of the search space according to a constraint, thus enabling the optimizer to find the objective in the new space defined by the learned representation. Preliminary experiments show promise: compared to an identical GA using a standard representation that cannot meet the constraints or find fit solutions, COIL with its learned latent representation can perfectly satisfy different types of constraints while finding high-fitness solutions.
Type: | Proceedings paper |
---|---|
Title: | COIL: Constrained optimization in learned latent space: learning representations for valid solutions |
Event: | Genetic and Evolutionary Computation Conference (GECCO '22) |
ISBN-13: | 9781450392686 |
Open access status: | An open access version is available from UCL Discovery |
DOI: | 10.1145/3520304.3533993 |
Publisher version: | http://dx.doi.org/10.1145/3520304.3533993 |
Language: | English |
Additional information: | This is an Open Access paper published under a Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/). |
Keywords: | Variational autoencoder, Learning latent representations, Genetic algorithm, Constrained optimization |
UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
URI: | https://discovery.ucl.ac.uk/id/eprint/10152718 |
Archive Staff Only
![]() |
View Item |