Skip to yearly menu bar Skip to main content


Conditioning by adaptive sampling for robust design

David Brookes · Jennifer Listgarten

Pacific Ballroom

Keywords: [ Monte Carlo Methods ] [ Generative Models ] [ Computational Biology and Genomics ]


We present a method for design problems wherein the goal is to maximize or specify the value of one or more properties of interest (e.g. maximizing the fluorescence of a protein). We assume access to black box, stochastic ``oracle" predictive functions, each of which maps from design space to a distribution over properties of interest. Because many state-of-the-art predictive models are known to suffer from pathologies, especially for data far from the training distribution, the problem becomes different from directly optimizing the oracles. Herein, we propose a method to solve this problem that uses model-based adaptive sampling to estimate a distribution over the design space, conditioned on the desired properties.

Live content is unavailable. Log in and register to view live content