Evolving Through the Looking Glass: Learning Improved Search Spaces with Variational Autoencoders

Peter J. Bentley, Soo Ling Lim, Adam Gaier, Linh Tran

Parallel Problem Solving From Nature (PPSN)
2022

Abstract

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.

Related Publications

Loading...

Related Projects

  • Item headline

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.

  • Item headline

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.

  • Item headline

    Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.

Welcome ${RESELLERNAME} Customers

Please opt-in to receive reseller support

I agree that Autodesk may share my name and email address with ${RESELLERNAME} so that ${RESELLERNAME} may provide installation support and send me marketing communications.  I understand that the Reseller will be the party responsible for how this data will be used and managed.

Email is required Entered email is invalid.

${RESELLERNAME}