SOURCE-LINKED INTELLIGENCE

Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization

arXiv · AI, language, vision and robotics · article · Sep 16, 2026 · UTC

Generative models are increasingly central to many de novo discovery pipelines, in which designs are generated at scale and filtered through virtual screens to determine a set of candidates to experimentally validate. While Bayesian optimization (BO) is a natural fit for this setting, as it uses past evaluations to guide future proposals, the computational overhead required for its sequential decision-making becomes a bottleneck when virtual screens are relatively cheap. We make BO practical in this regime by exploiting the unique combination of a linear model constrained to a spherical domain

Read original source ↗ Open in workspace

recordType

paper

region

Global