Skip to main content Skip to main navigation

Publikation

High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning

Antoine Grosnit; Rasul Tutunov; Alexandre Max Maraval; Ryan-Rhys Griffiths; Alexander I. Cowen-Rivers; Lin Yang; Lin Zhu; Wenlong Lyu; Zhitang Chen; Jun Wang; Jan Peters; Haitham Bou-Ammar
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2106.03609, Pages 0-10, arXiv, 2021.

Zusammenfassung

We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces. By adapting ideas from deep metric learning, we use label guidance from the blackbox function to structure the VAE latent space, facilitating the Gaussian process fit and yielding improved BO performance. Importantly for BO problem settings, our method operates in semi-supervised regimes where only few labelled data points are available. We run experiments on three real-world tasks, achieving state-of-the-art results on the penalised logP molecule generation benchmark using just 3% of the labelled data required by previous approaches. As a theoretical contribution, we present a proof of vanishing regret for VAE BO.

Weitere Links