Conditioning by adaptive sampling for robust design
[edit]
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:773782, 2019.
Abstract
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 stateoftheart 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 modelbased adaptive sampling to estimate a distribution over the design space, conditioned on the desired properties.
Related Material


