COIL: Constrained Optimization in Learned Latent Space: Learning Representations for Valid Solutions
This addresses constrained optimization challenges for researchers and practitioners by enabling more effective search in complex spaces, though it appears incremental as it builds on existing VAE and GA methods.
The paper tackles constrained optimization problems by learning a latent representation that only permits valid solutions, making optimization more feasible without specialized algorithms. Preliminary experiments show COIL perfectly satisfies constraints and finds high-fitness solutions, unlike a standard GA that fails to meet constraints or find fit solutions.
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.