Publication | Genetic and Evolutionary Computation Conference 2022


Constrained Optimization in Workshop on Learned Latent Space

We show for the first time how generative machine learning can learn a representation corresponding to a valid region of search space, enabling optimizers to search in the new latent space and always find solutions that satisfy constraints.

Download publication


COIL: Constrained Optimization in Workshop on Learned Latent Space. Learning Representations for Valid Solutions

Bentley, P. J., Lim, S. L., Gaier, A. and Tran, L

Genetic and Evolutionary Computation Conference 2022

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.

Associated Researchers

Soo Ling Lim

University College London

Linh Tran

Autodesk AI Lab

View all researchers

Related Resources



BOP-Elites: A Bayesian Optimisation Approach to Quality Diversity Search with Black-Box descriptor functions

An algorithm that efficiently tackles expensive black-box optimization…



A Learning Approach to Robot-Agnostic Force-Guided High Precision Assembly

In this work we propose a learning approach to high-precision robotic…



Assemble Them All: Physics-Based Planning for Generalizable Assembly by Disassembly

This work proposes a novel method to efficiently plan physically…



Inferring CAD Modeling Sequences using Zone Graphs

In computer-aided design (CAD), the ability to “reverse engineer” the…

Get in touch

Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.

Contact us