A decoupled Bayesian optimization method that samples candidate molecules from a VAE prior weighted by a structure-space Gaussian process's probability of improvement outperforms latent-space BO on low-budget molecular design tasks.
πbo: Augmenting acquisition functions with user beliefs for bayesian optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces
A decoupled Bayesian optimization method that samples candidate molecules from a VAE prior weighted by a structure-space Gaussian process's probability of improvement outperforms latent-space BO on low-budget molecular design tasks.