COIL: Constrained Optimization in Learned Latent Space – Learning Representations for Valid Solutions

by   Peter J Bentley, et al.

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 the use of a Variational Autoencoder to learn such representations. We present 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. We investigate the value of this approach on different constraint types and for different numbers of variables. We show that, compared to an identical GA using a standard representation, COIL with its learned latent representation can satisfy constraints and find solutions with distance to objective up to two orders of magnitude closer.


page 5

page 7

page 8


Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search

We consider multi-solution optimization and generative models for the ge...

Evaluating MAP-Elites on Constrained Optimization Problems

Constrained optimization problems are often characterized by multiple co...

Using a Variational Autoencoder to Learn Valid Search Spaces of Safely Monitored Autonomous Robots for Last-Mile Delivery

The use of autonomous robots for delivery of goods to customers is an ex...

GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation

Robots have been used in all sorts of automation, and yet the design of ...

Do not Choose Representation just Change: An Experimental Study in States based EA

Our aim in this paper is to analyse the phenotypic effects (evolvability...

Tip the Balance: Improving Exploration of Balanced Crossover Operators by Adaptive Bias

The use of balanced crossover operators in Genetic Algorithms (GA) ensur...

Dynamic Narrowing of VAE Bottlenecks Using GECO and L_0 Regularization

When designing variational autoencoders (VAEs) or other types of latent ...

Please sign up or login with your details

Forgot password? Click here to reset