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

A new arXiv paper (2609.19476v1) reports a latent space Bayesian optimization method that achieves at least a 100x speedup over state-of-the-art baselines while matching or improving performance on molecular and image generation benchmarks. The authors derive nearly closed-form solutions to the surrogate modelling and acquisition problems by exploiting a linear model constrained to a spherical domain where high-dimensional latents concentrate, building on recent work justifying linear surrogates. The method is positioned as a practical drop-in for de novo discovery pipelines where sequential Bayesian optimization was previously too slow to consider.

arXiv:2609.19476v1 Announce Type: new Abstract: 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 where high-dimensional latents concentrate. We build off recent work justifying the use of linear surrogates, while deriving nearly closed-form solutions to the surrogate modelling and acquisition problems that exploit spherical symmetry. The result is at least a 100x speedup over state-of-the art baselines, with matching or improved performance across molecular and image generation benchmarks. Altogether, our method makes BO a practical drop-in for de novo pipelines where it was previously too slow to consider.