Publication | Parallel Problem Solving From Nature (PPSN) 2022
Evolving Through the Looking Glass
Learning Improved Search Spaces with Variational Autoencoders
We show 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 or additional criteria. This work continues previous work and demonstrates the method for more complex constraints and additional criteria.
Download publicationAbstract
Evolving Through the Looking Glass: Learning Improved Search Spaces with Variational Autoencoders.
Bentley, P. J., Lim, S. L., Gaier, A. and Tran, L.
Parallel Problem Solving From Nature (PPSN) 2022
Nature has spent billions of years perfecting our genetic representations, making them evolvable and expressive. Generative machine learning offers a shortcut: learn an evolvable latent space with implicit biases towards better solutions. We present SOLVE: Search space Optimization with Latent Variable Evolution, which creates a dataset of solutions that satisfy extra problem criteria or heuristics, generates a new latent search space, and uses a genetic algorithm to search within this new space to find solutions that meet the overall objective. We investigate SOLVE on five sets of criteria designed to detrimentally affect the search space and explain how this approach can be easily extended as the problems become more complex. We show that, compared to an identical GA using a standard representation, SOLVE with its learned latent representation can meet extra criteria and find solutions with distance to optimal up to two orders of magnitude closer. We demonstrate that SOLVE achieves its results by creating better search spaces that focus on desirable regions, reduce discontinuities, and enable improved search by the genetic algorithm.
Associated Researchers
Soo Ling Lim
University College London
Linh Tran
Autodesk AI Lab
Related Resources
2024
A hyperreduced reduced basis element method for reduced-order modeling of component-based nonlinear systemsThis method balances accuracy and computational speed through adaptive…
2024
Exploring Opportunities for Adopting Generative AI in Automotive Conceptual DesignThis research discusses opportunities for adopting generative AI in…
2021
A Learning Approach to Robot-Agnostic Force-Guided High Precision AssemblyIn this work we propose a learning approach to high-precision robotic…
2021
Classifying Component Function in Product Assemblies With Graph Neural NetworksFunction is defined as the ensemble of tasks that enable the product…
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